AI Agent Tools: Skills

everything-claude-code299.3k★

ECC (formerly Everything Claude Code) is a big bundle of agents, skills, hooks, MCP configs and security tooling you install into Claude Code through the plugin marketplace. It covers code review, security analysis, planning, per-language reviewers, TDD workflows and even video editing. The repo is MIT licensed. It works best in Claude Code, has a supported Codex sync path, and offers capability-limited adapters for Cursor, OpenCode, Gemini, Zed, Copilot and others, so don't assume parity outside Claude. The bundle grows every release, now dozens of agents and a few hundred skills, and slash commands are being phased out in favor of skills. Install only from the official repo, npm packages or ecc.tools: the README warns third-party mirrors may carry malware. The repo is free. ECC Pro, a hosted GitHub App, is $19 per seat a month or $190 a year and adds private-repo analysis, PR-triggered config audits and deeper AgentShield scanning; Enterprise adds SSO and custom policy packs. Solo devs: install the free bundle and keep what you use. Teams that want automatic config audits on private repos: that's what Pro sells. The catch: that much surface area is a lot to audit. Hooks run automatically on editor events, and pulling in agents and skills you didn't ask for makes your setup harder to reason about. One maintainer ships it weekly across several harnesses, so expect churn.

ponytail186.5k★

Ponytail is a free rules pack that talks your coding agent out of writing code. Before typing, the agent climbs a seven-rung ladder: does this need to exist, is it already in the codebase, the standard library, a native platform feature, an installed dependency, one line, and only then the minimum that works, plus one small test for real logic. MIT licensed, nothing to host. Claude Code and Codex install it as a plugin in two commands. Windsurf, Cline, Aider, Zed and Kiro take a copied rules file without the slash commands. Commands cover intensity (lite, full, ultra), diff review, a whole-repo audit and a tech-debt ledger. Version 5's own benchmark (39 tasks, Opus 5.5, Claude Code) reports 53% less code, 26% lower cost and 41% faster runs than no skill. It's the maintainer's harness, so treat it as directional. Solo and small teams: free. Medium and large teams: free, and worth putting the review command into PRs. The catch: "write less" is a judgment call. A minimalist agent makes quieter mistakes, like reused code that almost fits. Start on lite and read what it declines to build.

gstack140.7k★

gstack is Garry Tan's Claude Code setup, open sourced by the Y Combinator CEO: 23 specialist slash commands that act like a virtual team (a CEO who rethinks the product, an eng manager who locks architecture, a designer, a reviewer, a QA lead who opens a real browser, a security officer and a release engineer), plus power tools like /office-hours, /review and /ship. All Markdown, MIT licensed. It's built for Claude Code, with experimental ports to Codex, OpenCode, Cursor, Factory, Kiro and Copilot CLI where its safety hooks are advisory rather than enforced. Install clones it into ~/.claude/skills/gstack and runs a setup script that needs Bun, and it keeps state in ~/.gstack too. Browser QA drives the Aside browser on macOS and falls back to its own Chromium. Solo founders and small teams who want an opinionated, ready-made workflow get the most here, free. Larger teams with their own conventions will mostly mine it for ideas. Telemetry stays off unless you opt in. The catch: it moves fast with no tagged releases, so your setup changes under you every time you pull. The optional GBrain setup can ask for a Supabase access token to create a project for you, so read what you're granting. And it's one person's taste, opinionated by design.

career-ops81.0k★

Career-ops turns the AI coding CLI you already use into a job-search filter. Paste a posting and it checks the job is still open, scores it 1 to 5 against your CV in an A-through-H report, then drafts a tailored resume PDF, cover letter and form answers. It never hits Submit. MIT licensed, no paid tier. Setup is one npx @santifer/career-ops init. Open Claude Code, Codex, OpenCode, Antigravity, Copilot or another CLI in the folder and it interviews you about your CV and targets. The scanner ships with 100+ companies preconfigured, a Go terminal dashboard tracks the pipeline, and an opt-in web UI is still alpha. Your data stays local except what goes to your AI provider. Solo job seekers: install it. The tool is free; your cost is the model, and free or local models work. One trap: an ANTHROPIC_API_KEY in your shell overrides a Claude Pro or Max login and bills per token. Small teams and larger orgs: not the audience. The catch: an LLM is rewriting your CV. A check blocks invented numbers, but its own FAQ says it doesn't yet verify job titles or judge rewording, so read every resume before it goes out.

security-audit-skill66.2k★

Cloudflare's security-audit skill turns a coding agent into a code auditor. A skill is a packaged set of instructions an AI agent loads for one job. This one maps your app's trust boundaries, sends isolated hunter agents through a coverage plan, then hands every candidate to a fresh agent that tries to disprove it before anything gets reported. It's the seed of Cloudflare's own fleet scanner, MIT licensed and free. Install is one command, npx skills add, then ask your agent to audit the repo. You need an agent that runs parallel sub-agents, plus Node for the bundled validators. It only executes the target's code inside a network-off sandbox. Without one, leads stay marked needs_validation. There's no paid tier. The bill is model tokens, and a full run spawns a lot of agents. Solo devs and small teams: free and a strong first pass. Larger teams: one input next to a human review. The catch: one run isn't enough. Cloudflare says a single run finds about half of what repeated runs catch, skewed toward simpler bugs. And its prompts don't tell agents to ignore instructions planted in the code they read, so a hostile repo could steer the audit.

agentic-awesome-skills49.3k★

This is a library of more than 2,000 reusable SKILL.md playbooks for coding agents. Skills are structured prompts that teach an agent a specific job (write tests, harden a web app, run a data pipeline), and the project installs them into Claude Code, Cursor, Codex, Gemini CLI, Kiro, OpenCode and others. MIT for the code, CC BY 4.0 for the content unless an upstream notice says otherwise, free. You install with npx agentic-awesome-skills plus a tool flag like --claude, and the installer now makes you choose: named skills, a risk, category or tag filter, or explicit consent for the whole catalog. The project itself says to start with a focused plugin instead. Newer releases add AAS Core, an optional local CLI and MCP server that lets an agent search the catalog and validate the skills it picks. For anyone building an agent workflow, this is a fast way to skip writing every skill from scratch. Solo developers and teams get the same value, since skills are just files you version alongside your project. The catch is curation. Thousands of community skills mean variable quality and overlap, and an installed skill is a prompt your agent will follow. The catalog labels some skills critical or offensive, and an audit command flags network, credential and destructive signals, but the project calls that a review aid, not a safety certificate. Read the ones you install.

watermarks-remover26.6k★

watermarks-remover strips AI provenance marks: invisible Unicode in text, and C2PA, EXIF and XMP metadata from images, PDFs, Office files, audio and video. Optional add-ons go after the statistical watermarks hidden in AI text and pixels, including SynthID-class marks. Visible stock-photo watermarks are untouched. It ships as an agent skill and Claude Code plugin over a local Python service, MIT licensed and free. The core is easy: make serve or Docker Compose, and the skill calls it over HTTP. A hook can check every file your agent writes. The add-ons are not: text rewriting needs an LLM backend, and pixel removal wants a GPU and about 10GB of models from an upstream repo with no license file. There's no paid tier. Solo and small teams: free, and the metadata cleanup is useful hygiene. Larger teams: free, but get legal sign-off before anyone runs the removal add-ons. The catch: this grew from hygiene into attacks. v0.7.0 added a watermark-stealing module, audio and video watermark removal, and its rewrite benchmark scores human-likeness with Pangram, a commercial AI-text detector. Its own ethics page rules out passing AI text off as human. China bans tools that help others maliciously strip AI labels.

claude-obsidian16.3k★

claude-obsidian turns a folder of Markdown into a research wiki your AI agent maintains. Drop papers, articles or transcripts into inbox/, and Claude Code writes linked notes that cite their sources, browsable as a graph in Obsidian. It's a Claude Code plugin plus Agent Skills, MIT licensed and free. Setup is two claude plugin commands and Python 3.11+; Codex, Gemini, Cursor and others hook in through a script. Version 3 ships 15 skills and 3 read-only agents, can file notes PARA or Zettelkasten style, and applies each change as one transaction that rolls back if a write dies. No telemetry. Windows needs WSL. Nothing is paywalled. The cost is tokens: every ingest, query and lint runs on your Claude plan or API key. Solo researchers and writers: free, and built for you. Small teams: free, sharing a vault through git. Larger teams: the write lock covers one machine, so treat it as personal. The catch: PDFs and EPUBs get no built-in text extraction yet, and web pages need a separate fetch step, so research inputs need extra tooling. And an agent writing your notes writes its mistakes confidently. Citations tell you where a sentence came from, not whether it's true.

prompt-master15.7k★

Prompt Master is a Claude skill that writes prompts for your other AI tools. Ask for "a prompt for Cursor to refactor my auth module" and it identifies the target tool, asks at most three clarifying questions, picks one of 13 templates, and returns one paste-ready prompt. Profiles cover coding agents, chat models, and image, video and voice tools. MIT licensed and free. Setup is a ZIP upload in Claude.ai's skill settings (the author's recommended path) or a git clone into ~/.claude/skills. Nothing to host. The main file runs about 5,000 words and loads into context whenever the skill fires. With chat history, it prepends a short "Memory Block" of earlier decisions so the new prompt doesn't contradict them. No paid tier; it runs on the Claude plan or API you already pay for. Solo: free, most useful if you juggle many AI tools. Small and larger teams: free, a decent baseline for briefing agents, not a replacement for your own prompt library. The catch: the model advice is hardcoded text, only as current as the last commit, and users have already flagged stale guidance. "Zero tokens wasted" is marketing; the skill costs thousands of tokens per run.

dbskill11.3k★

dbskill is a pack of 34 Chinese-language business skills for AI agents from the creator dontbesilent. Not coding skills: diagnosing why a business is stuck, finding competitors worth copying, planning content, writing short-video titles and hooks, checking scripts for platform moderation risk. The method comes from 16,152 of the author's public posts. Install is one npx skills add command or the Claude Code plugin marketplace, and it runs in Claude Code, Codex, Doubao, WorkBuddy and other skill-aware agents. A /dbs router picks the right skill for you. Nothing to host. Everything is in Chinese, so answers come back in Chinese. Most skills cost only your agent's tokens. Video extraction is the exception: it needs paid TikHub and Qingdou API credits and walks you through buying them. The README also links a paid Q&A group with the author at ¥299 (about $42). Solo creators: free for personal use. Small teams and up: get the author's sign-off first. Engineering teams: skip it. The catch is the license. CC BY-NC 4.0 means non-commercial only, and the README says commercial use needs the author's authorization. A business toolkit you can't freely use in your business is an odd shape. Read the terms first.

skills11.1k★

This turns Sahil Lavingia's Minimalist Entrepreneur methodology into Claude Code skills. Ten of them install through the plugin marketplace: find a community, validate an idea, scope an MVP, processize, find first customers, set pricing, plan marketing, grow sustainably, define company values, and run a minimalist review. Instead of reading the book and trying to apply it, you invoke a skill and the agent, prompted to act as an advisor channeling the book's philosophy, walks your specific situation through the framework. It asks questions, works through your answers and hands back structured output. The skills are free; you need Claude Code to run them. The catch is that this is one founder's business framework, not a technical tool. Output is only as good as your inputs, and if you disagree with the minimalist approach you will disagree with the advice. The repo has not been updated since April and ships no LICENSE file, only an MIT declaration in its plugin manifest, so be careful about reusing the prompts.

universal-modder9.5k★

Universal Modder turns Claude Code (or Codex, Gemini CLI, Cursor and others) into a game-modding agent. It bundles skills for engine fingerprinting, reverse-engineering playbooks, asset generation, in-game testing and packaging, plus a Python CLI that scans your Steam, Epic and Xbox installs and ranks the routes for modding each game. MIT licensed. Install it as a Claude Code plugin; you also need Git, Python 3.10+ and ffmpeg, plus Blender for 3D-to-sprite renders. Asset generation runs through fal's hosted models with a fal API key, or a local ComfyUI server for images without one. It asks before driving your mouse and keyboard, installing loaders into game folders, or publishing. The plugin is free; the art isn't. fal bills per generation, about $0.08 per image on the default editing model, with 3D, sound and voice priced separately, and the skill tells the agent to warn you before running more than about 20 generations. Solo hobbyists modding games they own are the audience. The author works at fal, which the README doesn't mention. The catch: the safety rules (no injecting into online games with anti-cheat, no cheats against other players, hands off DRM) are instructions to the agent, not enforcement. Its scope covers multiplayer games and servers you host, and the shared knowledge base already includes WoW private-server notes. It launched in late September 2026 with no versioned releases yet.

replica-skill8.3k★

Replica is eleven Claude skills that walk an agent through rebuilding someone else's app: map its screens and flows, plan the stack, build, test, score against the original, rename and ship. The standout is the Entrepreneur skill, which ranks what users complain about in real reviews so your version fixes it. MIT, no signup, no API key. Install is copying eleven folders into ~/.claude/skills/. The six helper scripts are standard-library Python with no network imports: a screenshot layout diff, a parity score, a review ranker that drops unlinked quotes, and a sweep that blocks deploy while the original's name or colors remain. The real cost is agent time; the author says a booking tool is weeks. Solo builders and small teams: a decent competitor-build checklist. Larger teams already have a product process. The catch: "clone any app" is the headline, and the fine print walks it back to features and flows, clean-room style: no scraping behind logins, trademark checks, a lawyer before launch. Good guardrails, but they're prompt instructions, not enforcement, and the legal risk is yours. It's also one commit with five unmerged PRs, one reporting the plugin install loads none of the skills. Copy the folders.

awesome-codex-subagents6.5k★

This is a curated collection of subagents for OpenAI's Codex CLI, now past 170 entries across more than a dozen categories. Picture an app store of pre-built specialists: each subagent is a config file tuned for one job, testing, documentation, security review, database migration, and dozens more. You don't build these yourself. You browse the list, grab the ones that fit your workflow, and drop them into your Codex agents directory. They use Codex's native TOML format with Codex-specific fields like reasoning effort and sandbox mode. Codex does not spawn them automatically, you delegate to them explicitly. The collection is free. You pay for Codex usage through your OpenAI account. It is community-maintained and still growing, so the catalog keeps expanding. The catch: this is a curated list, not a framework. Quality varies across the entries. Some are polished, some are experiments. And it is Codex-only. It does not work with Claude Code, Cursor, or other AI coding tools, so the value evaporates the moment you switch assistants.

day-trader-skill6.0k★

Day Trader Skill is 11 Claude skills that walk a day trade end to end: scan charts for setups, pull the news, time the entry, set the stop and target, size the position, check your risk limits, and hand a ticket to your broker. The Python is standard library only and reads free public data from Yahoo Finance, SEC EDGAR, Nasdaq Trader and the House Clerk. MIT, no API key. Install it as a Claude Code plugin, add your name and email for SEC requests, done. The standout is the Time Machine: it replays the rest of the session 10,000 times from the stock's own recent bars and gives you the odds before you risk a dollar. Orders are optional and go through Alpaca's official MCP server (paper account by default, and paper trading is free) or the Interactive Brokers connector. The skill's script never sees your keys. Solo traders: free. Not a team tool. The catch is day trading itself. The author's own fine print says most day traders lose money. Yahoo's chart endpoint is unofficial and can lag, and the simulation only knows the last 60 days. One commit, no updates since. Paper trade first.

answer-me-with-html6.0k★

Answer Me With HTML turns your coding agent's long answers into a one-page HTML explainer with auto-laid-out flowcharts, timelines, trees and tables, or into a narrated explainer video. The agent writes a Markdown draft and a bundled Node script renders it, so the agent never hand-writes HTML. MIT licensed, needs Node 20+. Install it as a Claude Code plugin or with npx skills add. There's nothing to host: pages land in a folder in your home directory and open in your browser. The only network calls are a weekly version check against GitHub and ElevenLabs narration if you set an API key; otherwise videos use your Mac's built-in voice. No telemetry. This suits people who learn better from a diagram than a wall of terminal text: architecture walkthroughs, comparisons, plan reviews. Developers who live in SSH sessions, or want answers searchable in the transcript, should skip it, because the reply shrinks to two or three lines plus a file link. The catch: it's written to fire without being asked, even when plain text would do, and every page pops a browser window by default. Turn off auto-open in its config or tell it to run only when you ask, or it gets noisy fast. It launched in October 2026 and ships several releases a day.

leanrea4.1k★

leanrea is one 8 KB instruction file that teaches your coding agent to reverse engineer shipped software: Electron apps, native binaries, Go builds, APKs, databases and websites. It replaces REA (Reverse Engineer Anything), an MCP server (a plugin that hands the agent extra commands) with 207 tools. leanrea skips the wrapper and tells the agent which real command to run. Free, MIT licensed. Install is npx skills add aicodeking/leanrea, for Claude Code, Codex, Cursor and others. Nothing to host, but the underlying tools must be on your machine. In the author's 36-run benchmark, leanrea finished 38% faster and 35% cheaper than REA, scoring 74 of 75 against REA's 75. The totals match the raw results file. Solo, small teams and larger teams: free. You pay only for model tokens. The catch: it's the author's own test, three reps on one Mac, and REA has shipped newer versions since. The README admits the bare model already handles most of this. Nine Router commands break when an agent copies them raw, and the fix is still an open pull request. You're also giving an agent shell access to untrusted binaries, so work on a copy, ideally in a VM.

wewrite3.7k★

Wewrite is a Claude Code skill that handles trending topic research, topic selection, article writing, SEO optimization, and publishing. Built for the Chinese content market. The pipeline goes from identifying trending topics on Chinese social platforms to generating articles optimized for WeChat's distribution algorithm. It covers the entire workflow that content teams typically do manually across multiple tools. The catch: Chinese-language tool for a Chinese platform. If you don't publish on WeChat, this is not for you. AI-generated content at scale raises quality questions regardless of platform, and WeChat has its own content policies around automated publishing that you need to understand before running this at volume.

tstack3.1k★

tstack is Theo Browne's personal set of agent skills for Claude Code and Codex, published under MIT. All nine are about getting a code change to a merged pull request while you're elsewhere. full-send finishes the change, proves it, files the PR, babysits CI and review bots, then merges. council gets reviews from three models from different providers and loops until they agree. Install is a git clone and a copy into your skills folder. You need an authenticated GitHub CLI and Python 3, and the skills call each other, so install the set. They're tuned for T3 Code, Theo's free agent app, with fallbacks elsewhere. Each council round runs three flagship models at high reasoning effort, so watch your usage. Solo devs shipping many small PRs benefit most. Small teams: read the merge rules before anyone types the trigger. These are prompts, not software, so edit them to fit your repo. The catch: saying "full send" lets the agent merge and force-push its own branch, and it overrides ask-first testing rules in your project files, including computer use. It won't bypass branch protection. If "ask before merging" is your only guardrail, two words remove it.

yomiyasu2.9k★

Yomiyasu rewrites AI-generated Japanese into Japanese that reads like a person wrote it. It targets the tells: stacked metaphors, fuzzy subject-predicate links, decorative formatting, copywriter phrasing. Its top rule is to keep each sentence's claim, emphasis and strength unchanged and never add information. It's an MIT agent skill for Claude Code, Codex and Cursor. Install with npx skills add nanaism/yomiyasu. Two optional Python checkers, a linter and an original-versus-rewrite diff, use only the standard library and make no network calls. Without Python the skill falls back to checking by eye. Separate modes handle tech writing, business documents and essays. Anyone publishing Japanese docs, PR descriptions or internal reports drafted with AI should try it; it costs only the tokens your agent spends. Everyone else can skip it, since it only does Japanese. The author is an ALGO ARTIS engineer, but the README says plainly this is a personal project, not a company product. The catch: the instructions are long (around 44 KB) and load into context every time the skill triggers, and the README warns it can conflict with other Japanese style skills. It's also a one-person project that went from launch to v1.0.7 in under a week.

headcount2.6k★

headcount packages Claude Code skills the way a company packages people: 16 departments covering things like security, finance and engineering, 172 skills in total, each department installable on its own. Rather than dumping every skill into one project and hoping the model picks the right one, you add the departments a project needs. Skills are addressed as department:skill, so security:threat-modeling and finance:unit-economics never collide. MIT licensed. Installation is two lines in Claude Code: add the marketplace, install a department. There is no server, no runtime, and nothing to keep patched. The whole thing is Markdown, which is also the honest description of what you are installing. An interactive org chart on the project site lets you search every skill and jump to its source before you commit to any of it. Free, all of it, with no paid tier. Solo builders and small teams get the most value, since the appeal is scaffolding you did not have to write. Larger teams should read the skills they install rather than trusting the department label, because these become instructions your agent follows. The catch is that 172 skills is a claim about volume, not quality, and the project is very new. Skill collections rot fast as the underlying agent changes, and a stale skill that confidently tells your model the wrong process is worse than no skill at all. Install the two departments you need, not all sixteen.

BeautifulRust1.8k★

BeautifulRust teaches your coding agent to write Rust like a careful Rust developer instead of someone wrestling the borrow checker. Three Agent Skills (write, review, and port from C, C++, Python, Go or JavaScript) plus a drop-in clippy config, distilled from five sources including the Rust API Guidelines and Effective Rust. MIT and free, for Claude Code, Codex, Copilot, Cursor and Gemini CLI. Install is one command: npx skills add morganlinton/BeautifulRust. The lint config is the part I'd take even without an agent. It flags unwrap outside tests, unsafe without a SAFETY comment, bool parameters and lossy casts, and the repo ships a crate proving every lint fires. Solo and small teams: free, install it today. Larger teams: put the clippy config in CI. In the author's benchmark Codex went from 53 to 76 of 85 checks with the skills, Claude Code from 72 to 80. The catch: that benchmark is one run per configuration, graded by a Claude model, and the author says so. The skills made Claude worse on the Bevy task. And the lints are strict: drop them into an existing crate with -D warnings and your build lights up before it helps.

pm-claude-skills1.5k★

pm-claude-skills is a library of ready-made skills you install into Claude Code or another AI agent to give it senior-professional workflows. Think PRDs, launch plans, and postmortems, around two hundred structured templates across twenty-plus fields, installed with one npx command and exportable to ChatGPT, Gemini, or Cursor. MIT, free. There is nothing to host; these are local Markdown files your agent reads. The value is entirely in the templates, so it lives or dies on whether the bundled frameworks match how you actually work. Across two hundred-plus skills the quality will be uneven, and a generic PRD template is only as useful as your willingness to adapt it. Treat it as a starting library, not gospel. This is for product managers and other knowledge workers using an AI agent who would rather start from a structured template than write every prompt from scratch. Solo or team, it is free. If you already have refined prompts you trust, or you bristle at one-size-fits-all frameworks, you will not get much from it. The catch is that this is content, not software. It does not make your agent smarter; it gives it scaffolding. Good scaffolding saves time. Generic scaffolding just adds a step. Skim what is in the box before you build a workflow around it.

golive-skill1.4k★

GoLive is an agent skill that takes the app your coding agent built and puts it live on accounts you own: hosting on Vercel or Netlify, a Supabase or Neon database, a domain from Porkbun or GoDaddy, email through Resend, and Stripe in test mode. The agent detects your stack, writes a plan, waits for your approval, applies it and checks the result. MIT, free, works with Claude Code and Codex. It's a Node CLI with no dependencies and no account, talking straight to each provider's API. Credentials sit in plain text files with owner-only permissions, not a keychain. It's alpha: promotion and rollback are only tested against mocks so far. Solo builders shipping a first app who want the wiring done on accounts they control: try it on a throwaway project first. The repo's homepage points to Tofu, a separate managed hosting service at $9.99/mo, for anyone who'd rather not own the accounts at all. The catch is the one the README admits. The approval flags are arguments the agent passes for you, and an agent already logged in to your providers can change DNS, email and payments without them. Treat installing it like handing over the keys.

guard-skills1.3k★

Guard-skills is a pack of quality gates for AI coding agents. You point your agent at them and they run a second pass over the code it just wrote, catching the specific ways AI-generated code tends to fail: swallowed errors, hardcoded "success" returns, hallucinated APIs, tests that assert nothing. Free and MIT licensed. Five skills cover the bases. One guards general clean code, one guards test quality (mock abuse, duplicate tests, implementation-detail assertions), and one treats your docs as claims and verifies each against the actual code. Two more are specific to WordPress and WooCommerce, handling escaping, sanitization, and money math. Install is a one-liner through the skills CLI, with nothing to host. If you let an AI agent write code, this is a cheap safety net for catching the slop before it ships. It's complementary to your real CI tooling, not a replacement for it. Useful at any team size, though heavier teams will still want proper linters and human review on top. The catch: it's brand new, just a couple of commits in, and tied to agents that support the skills format. Half the pack is WordPress and WooCommerce specific, so a general developer really gets three of the five skills. Worth watching as it grows.

autoprompt-skill1.2k★

Autoprompt is a skill that runs the loop for your coding agent. You hand it a goal, constraints, and success criteria, and it scopes, implements, tests, reviews, repairs, and verifies without you prompting each step. It installs into Claude Code, Codex, Copilot, OpenCode, and others through a single npm CLI. MIT licensed. The install story is the polished part. npm install -g autoprompt-skill, run autoprompt, pick your agent, confirm the path. A doctor --strict command checks every detected installation and uninstall is clean per provider, which is more lifecycle care than most agent skills bother with. It needs Node 20+, Python 3.11+ with PyYAML, and Bash 4.3+, so macOS and Linux unless you are in WSL. Free with no paid tier above it. The cost is tokens. A loop that implements, tests, reviews, and repairs makes many more model calls than you would by hand, and the project's own docs warn that on very small tasks the overhead works against you. The catch is how much weight the benchmark headline carries. The 45% fewer failures figure comes from a single Terminal-Bench 2.1 run, and the README says outright that timing and token logs were not retained, making the speed and cost numbers estimates from user reports. Credit for disclosing it. Measure on your own repo first.

ai-copywriter1.2k★

ai-copywriter is a prompt pack, not software. It's a portable agent "skill", a structured SKILL.md instruction set that teaches any capable LLM to write marketing copy using real copywriting frameworks and then strip out the tells that make text read as AI-generated. It bundles 33 specific fixes drawn from Wikipedia's "Signs of AI writing" list. Because it's instructions rather than code, it runs anywhere an agent runs: Claude, ChatGPT, Manus, whatever you've got. It's versioned, MIT licensed, and credits the upstream humanizer work it builds on, so it's a legit community project rather than a scraped prompt dump. For anyone using an AI assistant to draft landing pages, emails, or ads, it's a free upgrade to your output quality. Install it through the Skills CLI or as a Claude Code plugin and point your agent at it. The catch is exactly what it is: a Markdown file. There's no app, no guarantee, and results still ride entirely on the model you run it against. Treat it as a good starting prompt you'll still edit, not a copywriter in a box.

qiaomu-goal-meta-skill908★

qiaomu-goal-meta-skill is a skill for Claude Code and Codex that takes a vague request like 'build me an app' and turns it into a structured goal spec: clear success criteria, constraints, safety boundaries, and conditions where the agent should stop and ask. The point is to make an AI agent plan properly before it starts changing things. MIT, free, one command to install. There is nothing to run and no setup beyond adding the skill to your agent. It is narrowly scoped: it generates tight, bounded task specifications, with conservative defaults and pause-on-risk conditions baked in. It is also a young, single-commit project, and the documentation is primarily in Chinese with an English mirror, so set expectations accordingly. This is for people using a goal-style agent who keep getting burned by under-specified prompts and want guardrails between 'I have an idea' and 'the agent is editing files.' Solo or team, it is free. If you already write detailed, bounded task specs by hand, or you do not use a compatible agent, you will not get much from it. The catch is scope and maturity. It does one specific thing, generate disciplined goal specs, and it only helps inside a compatible agent. Treat it as a useful habit-former for agentic work, not a finished framework.

fablize888★

Fablize is a plugin for Claude Code that forces the agent to slow down and prove its work. Instead of letting the model declare a task done, it makes it reproduce the bug first, break the work into steps, and verify the result before claiming success. The pitch is procedural discipline: give a weaker model the working habits of a careful engineer without swapping the model. MIT, free, installs into Claude Code. There is nothing to host and no key to manage beyond the Claude subscription or API you already pay for. The whole thing is a discipline layer, not the intelligence. By the author's own admission it cannot make a model smarter, it can only make it more rigorous, which for agentic coding is often the part that actually fails. It is an early project, a handful of commits in, so treat it as promising rather than battle-tested. This is for developers already running Claude Code who keep getting confidently-wrong 'done' from their agent and want guardrails. Solo or team, the cost is the same: free. If you do not use Claude Code, or you do not run agentic coding workflows, there is nothing here for you yet. The catch is dependency. Fablize is only as useful as the agent it rides on, and its value is entirely in process, not capability. If your model is already disciplined, you will notice less. If it cuts corners, this is the leash.

compass-skills764★

compass-skills is a set of Markdown skills that help an AI coding agent manage long, multi-session work. It gets the agent to clarify the task, keep a repo-local memory of goals as a kind of task tree, hand off context cleanly between sessions, and follow your collaboration preferences. Everything stays in local plaintext, nothing is uploaded. MIT, free. There is nothing to run and no remote piece; the state sits as plaintext in your repo. It is narrowly aimed at the problem of agents losing the thread across long projects and multiple sessions. It is also very new, a couple of weeks old and mostly one author, so the conventions may shift and longevity is unproven. Early but pointed at a real pain. This is for developers running Claude Code or Codex on long-running projects who keep losing context between sessions and want persistent task memory. Solo or team, it is free. If your work is short and single-session, or you do not want to adopt another agent convention layer, skip it. The catch is maturity. The idea, giving an agent durable memory and clean handoffs, is a real one, but this is an early, single-author project, so bet on the concept more than the specific implementation. If it sticks, great; if it stalls, you have not lost much.

token-diet479★

token-diet is a set of rules you bolt onto a coding agent to make it stop wasting tokens. It trims the padding out of replies, docs, tests, and tool calls, the verbose scaffolding an agent emits by default, without dropping the parts that matter for correctness. Works with Claude Code, Codex, Cursor, Windsurf, and Cline through their session hooks. One-line install and it is free. There is no server and nothing to run. It installs a SessionStart hook or context file for whichever agent it detects, and you tune aggressiveness with flags, lite, ultra, or off when you want the agent verbose again. Because it works by steering style rather than intercepting traffic, setup is a single command and reversible in seconds. The pitch is money. The project claims roughly 31 percent lower bills on average, with a wide range, and output reductions from 30 to 81 percent on real Sonnet runs. Take the averages with salt, savings depend heavily on how you work, but the direction is right: terser agents cost less. Solo developers burning through API credits: try it, the downside is a one-line uninstall. Teams on metered agent usage: worth an A/B test before rolling out. The catch is that the repo ships without a stated license. No license technically means all rights reserved, so treat it as use-at-your-own-discretion until the author adds one, and know that terser output can occasionally clip context you actually wanted. Keep the off switch handy.