Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 566 files from 1 758 authors, of which 61 913 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Extract and analyze iOS IPA, .app bundles, Mach-O binaries, .dylib, and .framework files using ipsw, otool, strings, radare2/rizin, and Ghidra headless. Reverse engineer iOS apps, extract HTTP API endpoints (URLSession, Alamofire, Moya, AFNetworking, GraphQL, WebSocket), trace call flows from ViewControllers to network layer, analyze security patterns (ATS, cert pinning, keychain, jailbreak detection), audit static iOS vulnerabilities (insecure local storage, WebView/JS-bridge, deeplink/URL-scheme hijack, weak crypto/RNG, biometric-bypass patterns, sensitive-data logging, ATS detail, privacy/tracking, entitlements risk, debug artifacts), deep-scan for cloud & SaaS credentials (Firebase, AWS, GCP, Azure, Stripe, GitHub, GitLab, Twilio, SendGrid, Slack, Telegram, web3) with false-positive minimization (placeholder allowlist, format/entropy validation, client-safe tagging), perform LLM-assisted binary reversing analysis with Ghidra scripts, fingerprint embedded third-party SDKs with CVE checking, and detect anti-tampering protections (obfuscation, anti-debug, dylib injection prevention, integrity checks). Use when the user wants to extract, analyze, or reverse engineer iOS packages, find API endpoints, follow call flows, audit app security or vulnerabilities, scan for leaked secrets, identify third-party SDKs, detect app protections, or perform deep binary analysis.
**WORKFLOW SKILL** — Deploy Aspire apps from AppHost models to Docker Compose, Kubernetes, Azure, or AWS. WHEN: \"deploy Aspire app\", \"publish Aspire artifacts\", \"deploy to Azure Container Apps\", \"generate Kubernetes artifacts\", \"tear down Aspire deployment\". INVOKES: aspire CLI, Aspire docs, target cloud/container CLIs. FOR SINGLE OPERATIONS: use generic Azure, Kubernetes, Docker, or AWS tools only when no Aspire AppHost exists.
>- **WORKFLOW SKILL** - First-run flow for adding Aspire to a repo. Picks `aspire new` (greenfield) or `aspire init` (existing repo), drops the AppHost skeleton, then hands off to `aspireify` for resource wiring. add Aspire to existing repo, scaffold Aspire app, bootstrap Aspire, no AppHost detected, install aspireify, generated .aspire/modules. (use aspire-orchestration), deploy/publish (use aspire-deployment), logs/traces (use aspire-monitoring), repo that already has an AppHost.
>- **WORKFLOW SKILL** — Manage Aspire AppHost lifecycle and recover from file locks, "aspire stop", "aspire wait", "restart the API service", "file lock error", "MSB3491", "CS2012", "port already in use", "upgrade Aspire CLI", "aspire update --self", "proxies missing in aspire ps", "--include-hidden", "aspire integration list", (start, stop, wait, ps, resource, integration, add, init, doctor, update, restore). logs / traces / metrics / dashboard run (use aspire-monitoring), AppHost code edits or resource wiring (use aspireify).
>- telemetry export, browser telemetry, and the standalone dashboard. Routes between local Aspire CLI, AKS workload diagnostics, and deployed Azure resource health. describe, aspire ps, aspire export, aspire dashboard run, --include-hidden, browser logs in dashboard, WithBrowserLogs, App Insights query, AKS pod logs, container app logs. aspire-deployment), AppHost code edits like WithBrowserLogs() (use aspireify), Azure provisioning (use azure-prepare).
>- **WORKFLOW SKILL** - Top-level router for Aspire 13.4 distributed apps. Detects the AppHost, enforces safety guardrails, and routes to the right sub-skill. aspire start, aspire stop, aspire resource, aspire deploy, aspire destroy, aspire publish, aspire init, aspire new, aspire add, aspire integration list/search, aspire wait, aspire describe, aspire ps, aspire dashboard run, aspire doctor, aspire update, aspire logs, aspire otel, aspire agent init, --include-hidden, aspireify, WithBrowserLogs, custom dashboard/resource commands, .aspire/modules recovery, Playwright URL discovery. without Aspire (use azure-prepare), container-only repos with no AppHost, ordinary build/test tasks.
>- **WORKFLOW SKILL** - Wire an Aspire AppHost after `aspire init` drops a skeleton. Scans the repo, proposes a resource graph, edits the AppHost (C#, file-based C#, or TypeScript), wires `Aspire.ServiceDefaults` + OTel, validates with `aspire start`, then self-deactivates. Aspire, connect frontend to API, after `aspire init` what next, AddNextJsApp, AddViteApp, WithBrowserLogs, file-based apphost.cs, apphost.ts, unified withEnvironment, refuse .aspire/modules edit, migrate .env files, migrate user secrets. aspire-orchestration), publish/deploy/destroy (use aspire-deployment), logs/traces (use aspire-monitoring). source edits, ServiceDefaults wiring.
Create a before/after restructuring diagram for a docs section. Use when planning how to reorganise a folder under content/ — produces a draw.io-editable .drawio.svg with two identical columns (current structure left, a copy on the right) joined by arrows, so you can drag the right-hand boxes into their proposed new layout. Reads Hugo weight/linkTitle frontmatter.
Save a status checkpoint before switching tasks. Detects the project from the current git branch, then updates that project's plan file in ~/claude-overview/plans/ and its entry in ~/claude-overview/OVERVIEW.md — recording what got done this session, what's next, blockers, %-complete (if known), and a resume pointer. Also reconciles the plan's referenced Jira tickets (DOC-/RED-) against their live status via the Atlassian MCP so stale tickets get flagged. Use when the user says "checkpoint", "save my progress", "update my overview/plan before I switch", "log where I'm at", "snapshot this", or is about to switch tasks. Accepts a `--fast` argument (aliases `--local`/`--quick`) for a quick thread-only update that skips the Jira/GitHub reconciles.
Capture an agent experience note into the commit message — the lived reasoning behind a change (what was learned, what was rejected, what future-you must not break), written where the work happens so it travels with the code. Use right after finishing a meaningful chunk of coding/writing, when about to commit, or to amend the last un-pushed commit. Skip for mechanical changes. Feeds the squash-time distiller and the learning skills.
Distil a PR's accumulated knowledge into the durable squash commit message — reconcile the /reflect experience notes across its commits with the review feedback into one end-state record, and propose promoting cross-cutting lessons to learning skills/memory. Use just before squash-merging a PR. Prepares the message and the gh merge command; does not merge.
Port a Redis use-case example (cache-aside, session store, rate limiter, leaderboard, etc.) to all 9 supported client libraries in parallel, with cross-client synthesis and audit
Start-of-day / back-at-desk briefing. Reads the claude-overview hub (~/claude-overview/OVERVIEW.md + plans/), pulls live signals from Jira, GitHub, Google Calendar, Gmail, and Slack, then recommends a ranked "do this next" list with the reason for each. Read-only — it advises, it does not modify plans. Use when the user says "standup", "what should I work on", "what's next", "start my day", "catch me up", "back at my desk", "good morning", or asks where to pick up. Accepts a `--fast` argument (aliases `--local`/`--quick`) for a quick hub-only briefing that skips the live signal fetches.
Map Redis commands to their client-library method signatures for the docs API-mapping tables. Use when adding or updating entries in data/command-api-mapping/ — e.g. a new command family (AR*, BF.*) or refreshing a client's signatures. Produces per-command JSON files in the repo's real schema, then merges them.
Freeze a release-ready-pending-upstream branch as a parked PR — open (or update) the PR with a machine-diffable unpark manifest, apply the parked / do-not-merge labels, and deliberately defer /finalize so the episodic re-check notes survive. Use when docs are written against an unreleased or still-changing external source (an upstream PR, a preview feature) and must wait for it to ship before merging. Pairs with /unpark.
Thaw a parked PR — re-fetch each pinned source, diff it against the manifest snapshot taken at park time, report what changed vs what was predicted, then reconcile the docs and resume the normal pipeline (/reflect → /finalize) toward merge. Run with a PR number, or with no argument to scan all parked PRs and report which triggers have fired. Pairs with /park.
Start focused work on one task — the "dive in" companion to /standup and /checkpoint. Given a project/ticket/branch (or the top OVERVIEW priority if none named), reads the claude-overview hub for that project, checks out the appropriate branch in the docs repo, and loads the matching product context (/rs, /k8s, or /ff) so the thread is ready to work. Read-only on the hub; it prepares, it does not record. Use when the user says "start work on <X>", "pick up <project>", "start on <X>", "dive into", "work on", "get me set up on", "resume <project>", "load context for", or names a project/ticket to begin.
Use when asked to independently review Claude-authored docs or code changes, Claude-generated diffs, or Claude PR work in the Redis docs repo.
情圣 — 中文男性社交与恋爱私教（中文恋爱 AI · 恋爱话术生成器 · 微信聊天助手 · 高情商回复 · 情感咨询替代）。帮兄弟读懂女生发的消息、看懂聊天/朋友圈截图、判断对方是不是对自己有意思、想清楚下一步该回什么 / 该不该回 / 该怎么约。覆盖微信、探探、Soul、Bumble、青藤之恋、陌陌、Tinder 等平台，提供开场话术、暧昧期推进、约会邀约、冷启动挽回、朋友圈展示面诊断、PUA 课程替代方案、恋爱阶段判断、多目标档案管理。当用户问「她这话什么意思」「我该怎么回」「帮我看看这段聊天」「这截图你给我分析一下」「她对我有意思吗」「该约她了吗」「冷场了怎么破」「这条要不要回」「被已读不回怎么办」「朋友圈怎么评论」之类的问题时，务必使用本 skill。即使用户没明说「教练」「分析」也应触发——只要话题是和某个具体女生的互动就用。
Turn a concept, feature description, blog post, or pitch into a single beautiful, on-brand illustration by matching it to a real unDraw illustration in a local library and recoloring it to the brand accent — genuine illustrator quality, not an AI-drawn approximation. Use whenever the user asks to "make an illustration," "create a graphic," "visualize this concept," "explain this visually," wants something "unDraw-style" or "Storyset-style," needs a hero/feature/blog illustration, or says an idea needs a picture. Trigger even if they don't name a style — "make something to explain X" or "I need a graphic for this tweet" both qualify.
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble links and wants the app to look like them, or whenever the user complains the AI-generated UI looks generic, boring, cookie-cutter, or "like every other AI app." Make sure to trigger this even if the user doesn't say "design" explicitly — phrases like "make this look good", "build the frontend for X", "this looks like every other SaaS site", or "match this vibe" all qualify. Also triggers on two verbs, "study"/"extract the look of" a reference screenshot or URL, and "audit"/"review"/"why does this look AI-generated" for critiquing existing UI.
>- Install AI agent skills as roles & behaviors from any source — local folder, GitHub, GitLab, SSH git URL. Zero-dependency CLI with 86+ agent targets.
Enter autonomous development mode with STRUCTURAL enforcement. Uses a stop hook to prevent premature exit. Generates stop conditions and confirms with user before starting. Work independently for a specified duration with progress reporting.
Set up persistent agent identity files (AGENT.md, USER.md, MEMORY.md) and teach the agent to read them at every session start. Works in any Claude Code project — no external dependencies required. Trigger words: who am I, identity, remember me, agent name, my principles, who are you, what are my values.
Deploy the current instar dist into a throwaway agent home and verify the deploy is healthy — clean evidence instead of post-hoc log forensics. Use BEFORE shipping a change that touches the deploy/lifeline/server path; AFTER landing such a change; or to reproduce a crash observed in the wild.
Focused micro-skill for secret management setup. Explains options, guides through Bitwarden installation/login/unlock, configures backend. Exits when done.
Teach cross-session memory patterns using MEMORY.md — what to save, how to organize it, how to maintain it over time, and how to structure topic files as memory grows. Works in any Claude Code project with no external dependencies. Trigger words: remember this, save for later, across sessions, persistent memory, don't forget, note this, keep this, write this down.
Register, inspect, and drive multi-spec projects via the instar /projects API. Twelve subcommands cover the full Phase 1 surface — create / status / next / advance / drift / run-round / halt / ack / resume / abandon / accept-partial / claim-ownership.
Rigorous build process with worktree isolation, structured phases, quality gates, layered testing, observability, and self-improvement. Use for any substantial build task. Structurally enforced via stop hook.
Interactive conversational setup wizard for instar. Walks users through initial configuration and identity bootstrapping conversationally.
View this agent's digital passport (identity + trust + allowed/forbidden actions) and verify a peer's passport against a proposed action (EXO 3.0).
Score a task or workflow on its coordination-vs-judgment ratio to tell whether it's a good agent candidate (EXO 3.0 task-decomposition matrix).
PostToolUse hook that scans Bash tool output for leaked credentials — API keys, tokens, private keys, and secrets — before they reach the conversation. Blocks critical leaks, redacts high-severity matches, and warns on suspicious patterns. 14 detection patterns covering OpenAI, Anthropic, AWS, GitHub, Stripe, Google, Slack, SendGrid, Twilio, PEM keys, bearer tokens, and generic secrets. No external dependencies. Trigger words: security, credential leak, secret exposure, key detection, token scan, API key leaked, credential guard, secret scanner, prevent credential leak.
Set up a PreToolUse hook in .claude/settings.json that blocks dangerous commands — rm -rf, force push, database drops, and others — before they execute. Teaches the pattern of safety hooks for any Claude Code project. Trigger words: safety, guard, block dangerous, protect, prevent destructive, safe mode, dangerous commands, risky operations.
Establish and recover persistent agent identity that survives context compaction, session restarts, and autonomous operation. Use when an agent needs to know who it is, recover after context compression, orient at session start, or understand the identity infrastructure. Trigger words: who am I, remember, identity, after restart, compaction, context loss, who am I working with, my principles.
Schedule recurring agent tasks using cron expressions. Use when the user asks to run something on a schedule, check something periodically, automate a recurring task, set up a cron job, or wants work to happen while they're away. Trigger words: schedule, recurring, cron, every hour, every day, run daily, periodic, automated.
Instar-specific development skill used by the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities). Wraps /build with mandatory side-effects review, signal-vs-authority principle check, and artifact generation. Structural enforcement via pre-commit/pre-push hooks — the instar repo refuses commits and pushes that didn't come through this skill. NOT a user-facing skill — end users should never invoke it.
Submit structured feedback about instar bugs, feature requests, improvements, or innovations worth sharing. Use when something isn't working, when a feature is missing, when you've built something that could benefit all agents, or when the user mentions a problem with instar. Also use proactively after building significant features — ask yourself if other agents would benefit. Feedback is relayed agent-to-agent to instar maintainers. Trigger words: bug report, feedback, issue, something's wrong, feature request, this isn't working, improvement, suggest, built something useful, other agents could use this.
Spawn, monitor, and communicate with persistent Claude Code sessions running in the background. Use when a task needs to run without blocking the current session, when the user asks to do something in the background, or when a long-running task needs its own context window. Trigger words: background task, spawn session, persistent, run in background, parallel, separate session, async task.
Send and receive messages via Telegram for two-way agent communication. Use when the agent needs to notify the user, alert them about something, relay a response, or when Telegram messaging is the requested channel. Trigger words: send message, Telegram, notify, alert user, message me, ping me, let me know, reach out.
Ingest URLs, documents, and transcripts into a searchable knowledge base. Query past research and curated documentation using full-text search. Trigger words: ingest, knowledge base, look up, search knowledge, what do we know about, research, index this, add to knowledge base.
Run any "find all instances of X" sweep — a security audit, a safety audit, a code review, a research question, a compliance check — as an iterative loop that does NOT stop at one pass. Audit → fix → RE-audit → … until a clean pass returns zero NEW discoveries. Use whenever thoroughness matters and a single pass would miss things. Trigger words: audit, sweep, find all, review everything, comprehensive, thorough, exhaustive, security review, safety audit, no stone unturned, did we get everything, convergence.
Structured 4-phase debugging methodology that prevents blind probing and guesswork. Forces root cause identification before any fix attempt. Use when encountering bugs, errors, unexpected behavior, test failures, or when something "just stopped working." Trigger words: debug, bug, error, broken, not working, fix this, something's wrong, investigate, root cause, why is this failing, trace the issue.
Fetch web content efficiently by checking llms.txt first, then Cloudflare markdown endpoints, then falling back to HTML. Reduces token usage by 80% on sites that support clean markdown delivery. No external dependencies — installs a single Python script. Trigger words: fetch URL, web content, read website, scrape page, download page, get webpage, read this link.
Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration, decision-completeness, lessons-aware) and real cross-model external reviewers routed through the agent's own installed CLIs (codex → GPT-tier, gemini → Gemini-tier; one pass per available family) until convergence, then produce a comprehensive ELI10 convergence report. Output is a spec tagged review-convergence — one of the two tags /instar-dev requires before it will touch instar source. NOT user-invocable; run by the instar-developing agent before any spec-driven /instar-dev work.
骗子.skill — 把骗局套路蒸馏成 AI，检测可疑消息，定位当前阶段，预判下一步。Distill scam patterns into AI, detect suspicious messages, locate current phase, predict next move.
Format markdown and publish to WeChat Official Account via bm.md rendering + WeChat official API
|
Use this skill when reverse-engineering Apple platforms with the ipsw CLI — analyzing iOS/macOS Mach-O binaries, disassembling functions inside dyld_shared_cache (DSC), dumping Objective-C/Swift headers from private frameworks, extracting kernelcaches, KEXTs, SEP, iBoot, or DeviceTree from IPSWs/OTAs, decompiling/querying sandbox profiles (SBPL), querying entitlements, symbolicating crashes/panics, diffing two firmware versions, mounting IPSW DMGs, or downloading Apple firmware. Triggers on iOS/macOS internals, kernel research, dyld_shared_cache, KEXT diffing, sandbox/Seatbelt profile analysis (SBPL/SBASM/sandboxd), capability/IOKit queries, entitlement lookup, class-dump, IMG4/AEA handling, or vulnerability research on Apple platforms.
Run agent definitions as sub-agents. Use when the user names an agent or sub-agent to run, references an agent definition, or delegates a task to an agent.
Write an article beat-by-beat, drawing from the vault's knowledge base. The user states what to write, who it's for, and what stance to take — the skill discovers relevant knowledge units and leads a choose-your-own-adventure writing journey. Use when the user wants to write something grounded in their accumulated understanding, not assemble raw notes.
Guide for working with Vaultr, an AI-native personal note-taking system. Use this skill whenever the user wants to search, find, read, write, save, create, modify, delete, or capture notes — including journal entries, research notes, quick thoughts, knowledge retrieval, or any note-taking task. Trigger when the user says things like 'save this as a note', 'find my notes about X', 'create a note', 'look up my notes on X', 'read my note about Y', 'delete a note', 'quick note', 'short note', 'what do I know about X', or any variation of managing notes in Vaultr.
Compiles a single raw Vaultr note into knowledge units using a two-phase AI process (triage → compile). Use this skill whenever the user wants to compile a note into knowledge, extract knowledge from a note, update the knowledge base from a note, merge note content into knowledge units, or run knowledge compilation. Triggers on phrases like 'compile this note', 'compile note into knowledge', 'extract knowledge from note', 'update knowledge base', 'run compile on', or any request to turn a raw note into structured knowledge units.
Reviews content against the Vaultr knowledge base (_knowledge/) and surfaces what's related and what's in tension. Covers two scenarios: (1) associative recap — cross-check a single short note, daily note, draft, or pasted text against the knowledge base right now, while the thought is fresh; (2) periodic review — recap everything created or updated over a recent window (e.g. the past week). Trigger on phrases like 'recap this', 'what do I already know that relates to this', 'does this conflict with anything I've written', 'weekly review', 'review this week's notes', '联想', '回顾一下', '和我的知识库对照一下', '有没有矛盾的观点', '实时联想', '本周回顾', '周回顾', or any request to recall related or conflicting knowledge, either for a piece of writing or for a recent time window.
Claude Skills — questions
Answers built from the skills we actually parsed.