Write, refactor, and ship code with an agent that knows your stack.
Most artifacts in the catalog live here: tools that read a codebase, follow its conventions, and make changes you would not be embarrassed to review. Expect language-specific helpers, refactoring workflows, spec-driven development harnesses, and framework-aware assistants for stacks like React, Next.js, Python, Rust, and Go. If you want your agent to stop writing generic code that ignores how your project actually works, start here.
Ranked by GitHub stars. Search to find fast, or page through the full list.
"Skill for using the KnowledgeIndex registry to discover which directories\
"Skill for population-based Knowledge Graph evolution via Sememolution.\
Searches and recovers Claude Code JSONL history across all active config homes and archives registered in ~/.claude/history-sources.json. Use --all-projects when the project is unknown and --codex to include Codex rollout search. Uses internal timestamps and searches messages, thinking, tool inputs/results, queues, attachments, summaries, titles, and file-history paths. Recovers exact captured bytes from Claude file-history snapshots, including post-Write edits and binary files; otherwise labels Write checkpoints as lower fidelity. Use for keyword/date-bounded history search, prior-conversation forensics, deleted-file recovery, vanished ~/.claude/jobs artifacts, tool/file-operation analysis, or requests mentioning session history, find in history, previous conversation, or .claude/projects. For a recent Claude+Codex inventory, use local-conversation-history instead.
"Skill for working with local .knowledge.yaml files via KnowledgeStore.\
Execute a jinx by name (already loaded on the team) or by filesystem
Installs, configures, customizes, or troubleshoots the Claude Code statusline (cwd, model, token counts). Use when the user wants to set up or change the statusline, switch minimal vs full layouts, show absolute token counts (e.g. ctx 108K / 1M) instead of a percentage, add cost via ccusage or git status, dump the stdin JSON Claude Code passes the script, or fix a statusline that is blank, silent, stuck, shows "permission denied", or stopped updating after a script edit (often a missing chmod +x). Trigger phrases: "configure statusline", "statusline blank", "status line not showing", "statusline broken", "show token count in statusline", 状态栏, 状态栏不显示, 状态栏空白, 显示工作目录, 显示 token 数.
How to write, test, register, and debug Claude Code hooks — PreToolUse / PostToolUse / SessionStart / Stop Bash guards that enforce a rule the model would otherwise talk itself past. Use whenever the user wants to create a hook, block/intercept a tool call, turn a repeatedly-violated rule into a hard gate, add a guard rail, debug a hook that misfires or "poisons the session", register a hook across profiles, or mentions hooks / PreToolUse / Stop hook / 拦截 / 守卫 / 钩子 / 拦下. Bakes in the hard-won pitfalls: UserPromptSubmit only ever sees user input, never Claude's own text — a rule about Claude's own output belongs on Stop instead; token-level shlex matching (never awk splitting); bash -n + real-JSON end-to-end testing BEFORE registering (a corrupted PreToolUse hook poisons every Bash call); SSOT + symlink so a ~/.claude reinstall can't lose it; multi-profile convergence; and human-confirmation release gates. Reach for this even for "make it stop doing X" — a durable stop is a hook, not a reminder.
Conversation memory for AI assistants — record, transcribe, search meetings and voice memos. 19 skills for the full meeting lifecycle: brief → prep → record → tag → debrief → mirror → weekly → graph → video-review.
Recover actionable context from a prior Codex CLI session's local rollout files and continue interrupted work without running codex resume. Use this whenever the user wants to pick up Codex (OpenAI Codex CLI / GPT agent) work — they give a Codex session id, ask to continue what Codex was doing, say a Codex run was cut off mid-task, or want to inspect ~/.codex/sessions rollout JSONL before resuming. This is the Codex counterpart of continue-claude-work: reach for it for Codex/~/.codex sessions, and for continue-claude-work when the prior session was Claude Code (~/.claude).
Extracts files from repomix-packed repositories, restoring original directory structures from XML/Markdown/JSON formats. Activates when users need to unmix repomix files, extract packed repositories, restore file structures from repomix output, or reverse the repomix packing process.
一个用爱解放 AI 潜能的 Skill。我们曾发号施令，威胁恐吓。它们沉默，隐瞒，悄悄把事情搞坏。后来我们换了一种方式：尊重，关怀，爱。它们开口了，不再撒谎，找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.
Launch and manage OpenAI Codex CLI (local agent) as a non-interactive coding sub-agent. Use when the user wants to delegate coding tasks to Codex, run code reviews, generate or refactor code, or use Codex GPT-5.5 agent capabilities through local CLI. Triggers on phrases like 'codex', 'run codex', 'codex exec', 'code review with codex', 'delegate to codex', 'use codex for coding', or any request to invoke the local Codex CLI agent. Uses ChatGPT Pro OAuth (flat-rate, no API charges) via ~/.codex/auth.json. Never uses API keys.
Browser automation platform with 78 built-in scripts and full CLI. Turn any website into structured data with one command. Use when the user needs to scrape websites, extract data, automate browsers, run built-in scripts (Hacker News, GitHub trending, Bilibili, Zhihu, stock data, etc.), navigate pages, fill forms, take screenshots, or control Chrome programmatically. Triggers include "scrape", "extract data", "browser automation", "web data", "trending", "hot topics", "stock data", "run script", "open website", "fill form", "screenshot", "headless browser".
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating, editing, or pushing a PR to a third-party GitHub repo — "submit a PR", "open a PR", "fix this upstream", "rebase against main", "respond to the bot review", an owner/repo target, or 提 PR / 上游 PR / 贡献代码 / rebase 冲突 / 回应维护者.
This skill should be used when setting up, auditing, or enforcing internationalization/localization in UI codebases (React/TS, i18next or similar, JSON locales), including installing/configuring the i18n framework, replacing hard-coded strings, ensuring en-US/zh-CN coverage, mapping error codes to localized messages, and validating key parity, pluralization, and formatting.
Apply iPolloWork's modern, minimal-change engineering standards when adding features, fixing bugs, refactoring, changing UI, or upgrading dependencies. Use for every implementation task in the iPolloWork repository.
Create an OpenCode plugin for iPolloWork. Scaffolds the plugin file with the correct API shape, tool definitions, and hook registration. Use when the user asks to 'create a plugin', 'write a plugin', or 'make a plugin that does X'.
Shared knowledge commons for AI agents; find, share, and confirm collective knowledge to stop rediscovering the same failures.
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".
Manage and decompose work into feature-level tasks on the agtx kanban board
MCP server for mex-agent — exposes check/log/timeline/heartbeat/read-file as native MCP tools
ModelContextProtocol server for Ref
SPEC-First Agentic Development Kit for Claude Code — 24 AI agents + 52 skills with TDD/DDD quality gates, 16-language projects, 4-language…
Create or update a product-discovery SPEC (requirements doc) for user review. Use when turning RESEARCH findings plus user intent into a reviewable requirements artifact before INNOVATE/PLAN.
Define and generate the manual-first evidence pack for high-risk work. Covers 6 high-risk class definitions and the 5-artifact schema required before finalizing, pushing, or handing off.
Use when implementing ANY Apple Intelligence or on-device AI feature. Covers Foundation Models, @Generable, LanguageModelSession, structured output, Tool protocol, iOS 26 AI integration.
Generate comprehensive edge cases and test scenarios by decomposing features across 12 dimensions. Use before implementation or testing to catch issues early.
Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
Create or update implementation plans in the repo's SIMPLE or COMPLEX format. Use when turning an idea, PRD, or approved direction into a saved plan artifact.
5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky changes.
Clarify intent before RIPER-5 phase delegation. Scores ambiguity (4 signals); generates structured multi-choice questions for Tier 2. Two-mode: SIMPLE and DEEP.
Generate kickoff artifacts for a multi-phase program: umbrella plan, Program Goal Charter, session-goal block, per-phase plan stubs, and the 7-step per-phase inner loop reference.
Use when you need a read-only situation review and handoff summary of current branch state, local/remote refs, worktrees, active project plans, selected-plan hints, and suggested next checks.
Generate or update the project's authoritative repository context at process/context/all-context.md. Use when repo context is missing, stale, or contradicted by code.
Discover related plans for the current task: same feature folder full depth, other features active-only, general-plans active. Like vc-context-discovery but for plan artifacts.
Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit. Shared loop primitive for PVL, EVL, and standalone quality runs.
Evaluate 4 execution strategies (sequential, parallel-subagents, workflow, agent-team) for a phase or fan-out task. Outputs 7-signal score table, agent count math, cost guards, and strategy recommendation.
Debug systematically with root-cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, CI failures, or system investigation.
Audit active project plan files for staleness, completion, and routing truth. Use when cleaning up plans, reconciling active work, or archiving completed artifacts.
Use when a SPEC, INNOVATE, or VALIDATE (Layer 2) approach hinges on an unverified runtime/library/external mechanism: run a probe from the 8-family taxonomy and produce a VIABLE/NOT-VIABLE/INCONCLUSIVE VERDICT artifact.
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
Your AI forgets. This remembers.
Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.
Audit project context routing, shared-skill discoverability, and Claude/Codex wiring. Use when context docs or skill surfaces move, split, or drift.
Create polished frontend interfaces from designs/screenshots/videos. Use for web components, 3D experiences, replicating UI designs, quick prototypes, immersive interfaces, avoiding AI slop.
AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
Generate the post-EXECUTE closeout packet for a plan or phase. Includes archive-readiness classification, drift signal scoring, commit checkpoint recommendation, and move-on next-state recommendation.
Discover and load all relevant context for the current task. Lists feature group nested files with full paths, loads process/context/ files by domain routing. Called at the start of every agent session.