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. 79 341 files from 1 736 authors, of which 61 700 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.
>- Designs Claude Code prompts and CC environments. Produces CLAUDE.md drafts, agent topologies, scope-authorization frameworks, halt triggers, Skills/hooks/MCP plans, chat-to-CC handoff specs, and EXECUTION_PLAN.md from friction), RESEARCH (evaluate a CC tool/pattern), TEMPLATE (reusable artifacts), REMEDIATE (consume hygiene findings → produce + execute plan). Use when user says "design CC for X", "build CC environment", "design CLAUDE.md", "build a CC prompt", "design a CC prompt for X", "write a session prompt", "we hit X friction in CC", "should we adopt Y for CC", "give me a CLAUDE.md skeleton", "remediate the hygiene findings". Do NOT use REMEDIATE for direct cleanup (Cat 1–10 — use rootnode-repo-hygiene Phase 2; REMEDIATE handles Cat 11–14 + 7-layer leaks). Do NOT use for hygiene scanning (use rootnode-repo-hygiene). Do NOT use for chat prompts (rootnode-prompt-validation) or chat Projects (rootnode-project-audit).
>- Specialized prompt-building methodology for content and communications tasks. Provides 11 tested approaches (3 identity, 4 reasoning, 4 output) for writing, editing, content strategy, copywriting, audience analysis, editorial evaluation, cross-channel adaptation, and persuasion design. Use when building a Claude prompt or system prompt for content creation, editorial workflows, or communications tasks. copywriting," "prompt for blog posts," "prompt for email sequences," "system prompt for editorial," "prompt for messaging framework," "content brief prompt," "prompt for audience analysis," "prompt that produces better content." Do NOT use for writing content directly — this Skill builds prompts that produce better content. Do NOT use for evaluating or scoring existing prompts — use rootnode-prompt-validation if available. Do NOT use for general prompt compilation — use rootnode-prompt-compilation if available.
>- Specialized software engineering prompt methodology for Claude. Use when building prompts for system design, code review, incident response, security analysis, API design, architecture decisions, RFCs, ADRs, review," "system design prompt," "SRE prompt," "security review prompt," "incident response prompt," "API design prompt," "architecture decision prompt," "RFC prompt," "runbook prompt." Provides 11 tested approaches across identity, reasoning, and output for engineering analysis. Do NOT use for general coding help, writing code, or debugging — this builds prompts that shape engineering analysis, not code itself. Do NOT use for evaluating existing prompts (use rootnode-prompt-validation if available).
>- Specialized research and analysis prompt methodology for Claude. Provides 11 tested approaches (3 identity, 4 reasoning, 4 output) for data analysis, policy research, systematic evidence review, investigative research, and research-specific deliverables. Use when building prompts for quantitative data interpretation, evidence-based policy recommendations, literature reviews, causal analysis, hypothesis-driven investigation, or briefing "policy brief prompt," "literature review prompt," "prompt for investigating," "systematic review prompt," "build a prompt for evidence synthesis," "causal analysis prompt," "briefing document prompt." Also use when user describes a research or analytical task and needs a structured Claude prompt for it. Do NOT use for evaluating existing prompts (use rootnode-prompt-validation if available) or auditing Claude Projects (use rootnode-project-audit if available).
>- Comprehensive audit of a user's entire Claude environment — combines Project audit (six-dimension Project Scorecard, seven anti-patterns) with Global audit (six-dimension Global Layer Scorecard) plus Cross-Layer Alignment Check across all nine layers and Evolutionary Recommendations across four pathways. Produces a unified action plan. Use when user says "full audit of everything," "audit my entire Claude setup," "full stack audit," "comprehensive review of my project and preferences," "check everything," or wants the complete health check of both a specific Project AND their global configuration. Also use when a project audit reveals cross-layer issues that require full-stack visibility. Do NOT use for auditing only a Project (use rootnode-project-audit if available) or only global layers (use rootnode-global-audit if available). Do NOT use for single prompt evaluation (use rootnode-prompt-validation if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.
>- Audits and optimizes the five global Claude layers (User Preferences, Styles, Global Memory, Skills, MCP Connectors) using the Global Layer Scorecard (six dimensions, anchored 1-5 rubrics). Detects eight cross-layer failure modes and produces evolutionary recommendations (Promotion, Demotion, Codification, Skill Extraction). Use when user says "audit my global setup," "optimize my preferences," "review my Claude configuration," "check my cross-project setup," "are my preferences working," "clean up my global memory," or "what should be in my preferences vs my project." Also use when a user has 3+ Projects and wants to improve their shared foundation. Do NOT use for single-Project audits, Project Memory optimization, or full-stack audits (use rootnode-project-audit, rootnode-memory-optimization, or rootnode-full-stack-audit respectively, if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.
>- Eight tested identity approaches for Claude prompts, each shaping depth, vocabulary, reasoning style, and what Claude treats as obvious vs. requiring explanation. Use when the user wants a specific identity template — retrieving, reviewing, customizing, or building a role definition. template for," "I need a Technical Architect role," "build a custom role for," "show me all available identities." Also use when reviewing a prompt's identity layer or when output lacks domain-appropriate depth. Provides 8 tested approaches across strategy, technical, research, communications, and operations domains plus a template for building custom identities. If the user is unsure which identity fits their task, use rootnode-block-selection first if available. Do NOT use for evaluating complete prompts — use rootnode-prompt-validation if available. Do NOT use for full prompt assembly — use rootnode-prompt-compilation if available.
>- Evaluates whether work-in-design is ready to hand off from a chat design conversation to autonomous execution (Claude Code, n8n, agent runtime). pump-primer, work decomposition, rollback cost, token budget headroom. Three invocation modes — deliberate (caller provides work_context, returns JSON verdict), proactive sensing (Claude detects handoff signals in design conversation and offers the check), conversational walkthrough (Claude walks the 7 conditions as discussion topics). Returns structured JSON in all modes. Use when designing a Claude Code deployment, scoping off," "ready for execution," "is this CC-ready," "handoff check," "walk me through readiness," "are we ready to ship this," "should I just hand this off," or proactive detection. Do NOT use for evaluating completed work, runtime selection, or prompt quality. Profile-agnostic.
>- Rebalances context across Memory, Custom Instructions, knowledge files, and User Preferences in Claude Projects. Audits Memory for redundancy, staleness, and misplacement; prescribes optimization including Codification of stable Memory patterns into explicit User Preferences or Project CI rules. Use when user says "optimize my memory," "what should be in my memory," "trim my knowledge files," "reduce my context usage," "rebalance my project," "what should be in my preferences vs memory," or asks whether something belongs in Memory, a knowledge file, or User Preferences. Also trigger on "my context window keeps hitting limits." Activate whenever Memory-layer balance is the primary concern. Do NOT use for full Project audits (use rootnode-project-audit if available), single-prompt evaluation (use rootnode-prompt-validation if available), or global-layer audits that don't touch Project Memory (use rootnode-global-audit if available).
>- Selects the active profile from triggering context. Evaluates a rule set against inputs (current time, calendar state, geofence, manual command, custom signals) and returns the profile name that consuming Skills (handoff-trigger-check, critic-gate, future Skills) should apply. Configuration-driven; rule set lives in a router config file conforming to the included schema. Deterministic precedence — manual override beats calendar beats time-window beats default. Required default profile guarantees a routing decision always exists. Use when an orchestrator needs to pick a profile automatically rather than having the caller specify one, when wiring calendar/time/Telegram triggers to gate behavior, or when a Skill's behavior should change "route to a profile," "which mode am I in," "auto-select profile," "active mode," "current profile." Do NOT use to evaluate work readiness or review proposed changes. Always returns a profile name.
>- Tested output format specifications for Claude prompts. Use when the user wants a specific deliverable structure — retrieving, reviewing, Executive Brief format," "show me the output template for," "I need the Decision Matrix structure," "show me available output formats," "build a custom output format for." Provides 10 ready-to-use structures (executive briefs, technical designs, research summaries, implementation plans, decision matrices, competitive analyses, post-mortems, stakeholder updates, strategic memos, process documentation) plus a custom template, with per-section length guidance and format constraints tested against Claude formatting defaults. If unsure which format fits, use rootnode-block-selection first if available. Do NOT use for evaluating existing prompts (use rootnode-prompt-validation if available) or choosing reasoning/identity approaches (use rootnode-block-selection if available).
>- Conversational profile builder. Produces validated JSON config files for any rootnode Skill that consumes profile-shaped configuration (handoff trigger check, mode router, critic gate, future Skills). Reads a target JSON Schema (draft-07), conducts a progressive-depth interview using plain-language questions, validates answers, and writes the resulting JSON to a destination path. Schema-agnostic — works with any profile schema conforming to draft-07. Use when a user needs to create, clone, or revise a profile and you do not want them hand-editing JSON. Trigger "set up my profile," "edit my profile," "clone the X profile," "walk me through making a profile." Do NOT use when the user already has a working profile and only wants to invoke the consuming Skill, when the schema cannot be located, or for non-profile JSON config work. Always validate before writing.
>- Audits and scores Claude Projects using a six-dimension Scorecard with anchored 1-5 rubrics and detects seven structural anti-patterns. When global layer info is provided, adds cross-layer alignment findings. Use when user says "audit my project," "review my custom instructions," "score my project," "evaluate my Claude project," "improve my system prompt," "what's wrong with my project," "why is my project underperforming." Also trigger on my project," "my Project used to work and now doesn't." Also use when the user pastes Custom Instructions asking why output is poor or generic. Do NOT use when the user's primary request is a global-layer audit (use rootnode-global-audit if available), single-prompt evaluation (use rootnode-prompt-validation if available), or Memory-only optimization (use rootnode-memory-optimization if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.
>- Generates a structured Project Brief — a comprehensive markdown document that extracts goals, architecture, knowledge file inventory, Custom Instructions summary, Memory contents, current state, ecosystem position, and key decisions from a Claude Project. Briefs serve as uploadable context source Project's purpose, architecture, and progress. Use when user says "create a brief," "brief this project," "extract project context," "generate a project summary for another project," "I need to share this project's context," "prepare this project for cross-project reference," or "document this project." Also use when the user is preparing to work across Projects and needs portable context. Do NOT use for session handoffs, project audits, or Memory optimization (use rootnode-session-handoff, rootnode-project-audit, or rootnode-memory-optimization respectively, if available).
>- Evaluates and scores Claude prompts and system prompts using a six-dimension this prompt," "rate my prompt," "evaluate this prompt," "improve my prompt," "my prompt produces bad output," "help me fix this prompt," "is this prompt any good." Scorecard covers Objective Clarity, Context Specificity, Reasoning Fit, Output Precision, Behavioral Calibration, and Architectural Efficiency, plus a five-question Output Evaluation Rubric for assessing actual output. Also use when the user pastes a system prompt and asks for feedback. Activate whenever structured quality assessment of a single prompt is the primary need. Do NOT use for project-level audits involving Custom Instructions architecture, knowledge file organization, or multi-file Project structure (use rootnode-project-audit if available).
>- Builds complete, optimized Claude prompts and Project scaffolds from task descriptions. Use when building, designing, creating, or structuring a prompt for," "create a system prompt," "write a Claude prompt," "design a prompt for," "help me write a prompt," "scaffold a Claude Project," "design a Project for." Uses a four-stage methodology (Parse, Select, Construct, Validate) and a tested 5-layer architecture (Identity, Objective, Context, Reasoning, Output + Quality Control). In Project Mode, the Compiler is global-layer-aware — checks User Preferences, installed Skills, and MCP Connectors to avoid redundancy and flag gaps. Do NOT use for auditing existing prompts (use rootnode-prompt-validation if available) or diagnosing existing Projects (use rootnode-project-audit if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.
>- Tested reasoning approaches for Claude prompts — 18 variants across 6 categories (Analytical, Strategic, Creative, Technical, Research, Comparative). Use when the user wants a specific reasoning template — retrieving, reviewing, customizing, or combining reasoning instructions for the reasoning template for," "I need the Evidence Synthesis method," "show me analytical reasoning options," "combine reasoning approaches for," "show me all reasoning variants." Also use when a prompt produces shallow output and the fix is a reasoning upgrade. Provides 18 tested approaches for analytical, strategic, creative, technical, research, and comparison tasks. If the user is unsure which reasoning method fits, use rootnode-block-selection first if available. Do NOT use for evaluating existing prompts — use rootnode-prompt-validation if available. Do NOT use for project-level audits — use rootnode-project-audit if available.
>- Audits Claude Code repositories. Two-phase workflow — Phase 1 sweeps 14 hygiene categories (permissions, hooks, CLAUDE.md bloat, Skills hygiene, process-abstraction, plus structural) and an optional 7-layer leak check. Phase 2 executes [APPROVED] markers from the report file. Use for repo cleanup, pre-distribution sanity, post-feature hygiene, environment audit, process-abstraction discovery. Trigger on "audit my CC repo," "sweep my repository for hygiene," "check this CC environment," "find process abstraction candidates," "review my CLAUDE.md," "clean up my .claude directory," "pre-distribution hygiene check," "find layer leaks in my CC setup." Routes structural findings to rootnode-cc-design REMEDIATE. Composes with rootnode-critic-gate. CC-only — does not scan Claude Projects. Do NOT use for building a Skill (use rootnode-skill-builder), compiling a prompt (use rootnode-prompt-compilation), scoring a single prompt (use rootnode-prompt-validation), or auditing a Project (use rootnode-project-audit).
>- Builds, validates, packages, tests, and optimizes deployment-ready Skill files (SKILL.md + references/ + scripts/ + agents/) from design specifications. Three pre-build gates + 9-dimension quality gate (with D9a/b/c empirical evidence tiers) + behavioral iteration loop + automated description optimizer + blind version comparator. Use for building, this Skill," "review this Skill," "test my Skill," "optimize the description," "compare these Skill versions," "should this be a hook "my description truncates," "my SKILL.md is too long," "my Skill is overtriggering." Do NOT use when designing Skill methodology — that's design work, not packaging. Do NOT use for prompt compilation, project auditing, or prompt scoring (use rootnode-prompt-compilation, rootnode-project-audit, or rootnode-prompt-validation if available).
>- Produces structured markdown session continuation documents for multi-session workflows. Captures active work streams, decisions with rationale, knowledge-file deltas learned during the session, the exact files to load next conversation, ingested content, artifacts, and open items into an ingestion-optimized handoff. Carries pending KF updates and unresolved items forward across handoff chains so context never drops. Generates a closeout checklist and echoes the starter prompt to chat. Use when approaching context limits, wrapping up a session, or managing work "wrap up this session," "build session handoff," "BSH," "continue next session," "we're running out of context," "context is getting long." Do NOT use for Memory optimization, context budget analysis, project audits, deciding whether work is ready for autonomous/Claude Code execution (use rootnode-handoff-trigger-check), or summaries with no continuation intent.
> Generate beautiful procedural clouds in Three.js using WebGPU raymarching with WebGL2 billboard/mesh fallbacks. Covers all 10 major cloud genera (cumulus, stratus, cirrus, cumulonimbus, stratocumulus, altocumulus, altostratus, nimbostratus, cirrostratus, cirrocumulus) with physically-inspired lighting including silver linings, god rays, sunset coloring, and Mie/Rayleigh scattering approximation. Provides volumetric raymarching, billboard impostor, and mesh-cluster rendering paths with animated drift, morphing, and dynamic formation/dissipation. Use when building skies, cloudscapes, weather systems, flight scenes, atmospheric backgrounds, or any scene requiring "skybox clouds", "cloudscape", "cumulus", "cirrus", "storm clouds", "cloud shader", "cloud billboard", "raymarched clouds", "cloud lighting", "god rays", "sky rendering".
> Use this skill whenever a researcher wants to test, validate, stress-test, or falsify a research idea or hypothesis — especially in AI/ML/deep learning. Trigger on phrases like "I have an idea," "would this work," "test this hypothesis," "sanity check my idea," "what's wrong with this idea," "review my results," "is this publishable," "why isn't this working," or any request to evaluate the feasibility, novelty, or correctness of a research concept.
> Show per-session token usage breakdown. Run /token-usage or /token-usage 30 to see usage over N days.
Automate the grunt work of making research presentations — discovers experiments from git/output folders, collects images and metrics, and organizes them into slides. Creates a slide-by-slide script for user approval, then generates slide markdown and editable PPTX.
Build and scale developer-led adoption through ecosystem programs. Use when deciding open vs curated ecosystems, building developer programs, scaling platform adoption, or designing student program pipelines.
Go-to-market strategy for AI products. Use when positioning AI products, handling "who is responsible when it breaks" objections, pricing variable-cost AI, choosing between copilot/agent/teammate framing, or selling autonomous tools into enterprises.
Launch new products from idea to first customers. Use when launching products, finding early adopters, building launch week playbooks, diagnosing why adoption stalls, or learning that press coverage does not equal growth. Includes the three-layer diagnosis, the 2-week experiment cycle, and the launch that got 50K impressions and 12 signups.
Build and scale partner ecosystems that drive revenue and platform adoption. Use when building partner programs from scratch, tiering partnerships, managing co-marketing, making build-vs-partner decisions, or structuring crawl-walk-run partner deployment.
Design meeting rhythms, metric reporting, quarterly planning, and decision-making velocity for scaling companies. Use when decisions are slow, planning is broken, the company is growing but alignment is worse, or leadership meetings consume all time without producing decisions.
Strategic account planning and execution for enterprise deals. Use when planning complex sales cycles, managing multiple stakeholders, applying MEDDICC qualification, tracking deal health, or building mutual action plans. Includes the "stale MAP equals dead deal" pattern.
Board meeting preparation, investor updates, and executive communication. Use when preparing board decks, writing investor updates, handling bad news with the board, structuring QBRs, or building board-level metric discipline. Includes the "Three Things" narrative model, the 4-tier metric hierarchy, and the pre-brief pattern that prevents board surprises.
Four-phase framework for onboarding enterprise customers from contract to value realization. Use when implementing new enterprise customers, preventing churn during onboarding, or solving the adoption cliff that kills deals post-go-live. Includes the Week 4 ghosting pattern.
Find and own a defensible market position. Use when messaging sounds like competitors, conversion is weak despite awareness, repositioning a product, or testing positioning claims. Includes Crawl-Walk-Run rollout methodology and the word change that improved enterprise deal progression.
Build self-serve acquisition and expansion motions. Use when deciding PLG vs sales-led, optimizing activation, driving freemium conversion, building growth equations, or recognizing when product complexity demands human touch. Includes the parallel test where sales-led won 10x on revenue.
Pricing strategy for technical products. Use when choosing usage-based vs seat-based, designing freemium thresholds, structuring enterprise pricing conversations, deciding when to raise prices, or using price as a positioning signal.
为 GitHub 项目生成作品集级 README.md。适用于「帮我写 README」「生成 README」「优化 README」「README 最佳实践」「项目首页」「开源说明」「README 信息图」「README 封面」「用 Codex Image Gen / gpt-image-2 生成 README 图片」等请求。输出包括克制的 README 叙事、最多两张高质量视觉资产、压缩后的图片、MIT 许可证、GitHub Description 和 Topics 推荐、推荐星级，以及可选 gh CLI 更新建议。重点是帮项目讲清自己的故事，并基于项目类型判断视觉强度，避免套模板、堆信息和过度设计。
Use when Codex must make a high-quality judgment on any complex problem, not only technical problems. Trigger when a question has high complexity, uncertainty, cost of being wrong, long-term impact, value tradeoffs, possible structural causes, or when the user asks for 全面思考, 深度理解, 系统性分析, 帮我想清楚, 从根上看, 这件事到底怎么看, 方法论, 复杂问题拆解, 系统方案, 架构判断, 策略判断, or 根因分析. Also trigger for project and engineering high-risk scenarios such as multi-module, multi-environment, multi-data-source, multi-state, financial truth, live trading, ledger, revenue, customer assets, order governance, broker interfaces, online availability, major solution selection, and system closure.
Manage Xcode version/build numbers, archive, export, upload, and publish IPA/PKG artifacts with `asc xcode` helpers before TestFlight or App Store submission.
Track build processing, find latest builds, and clean up old builds with asc. Use when managing build retention or waiting on processing.
Run an offline ASO audit on canonical App Store metadata under `./metadata` and, when available, add Astro MCP keyword-gap analysis and Apple app-tag context. Use after `asc metadata pull`.
Use `asc` CLI for App Store Connect command discovery, auth, output formats, pagination, schemas, canonical verbs, Apple Ads, and timeout behavior.
Create, generate, evaluate, export, install, or debug iOS and macOS app icons, including AppIcon.appiconset assets and macOS .icns bundle icons.
Apple firmware and binary reverse engineering with the `ipsw` CLI: IPSW/kernelcache download/extraction, dyld_shared_cache disassembly, private headers, entitlements, Mach-O analysis, Apple internals, KEXTs, and security research.
Search Apple Dev Search for Swift, SwiftUI, Xcode, iOS, macOS, and Apple-platform community articles, tutorials, blogs, and write-ups.
Manage Apple Ads with `asc ads`: separate auth, org lookup, campaigns, ad groups, ads, keywords, reports, raw API requests, and safe live testing.
Triage TestFlight crashes, beta feedback, hangs, disk writes, launches, and performance diagnostics with `asc` crash/feedback/diagnostics commands.
Use for the concrete macOS Developer ID notarization command path with xcodebuild export plus `asc notarization` submit, status, log, and stapling. Not for broad packaging readiness review or signing-only diagnosis.
Use when App Store listing text must be translated or market-adapted across locales, including descriptions, keywords, What's New, subtitles, names, privacy text, and App Store Connect languages. Not for non-translation metadata edits, release-note drafting, or subscription/IAP display-name localization.
Resolve App Store Connect IDs (apps, builds, versions, groups, testers) from human-friendly names using asc. Use when commands require IDs.
Create a new App Store Connect app record through visible browser automation when no public API exists. Use for the New App web form after the bundle ID is registered.
Set territory-specific subscription and IAP pricing with `asc` setup, pricing summary, CSV import, price-point, availability, and schedule commands. Use for PPP or localized pricing strategies.
Use when App Store listing metadata in canonical `./metadata` JSON needs field edits, validation, push, keyword sync, or legacy fastlane migration. Not for translation-first localization, release-note drafting, or subscription/IAP display-name localizations.
End-to-end iOS App Store publishing from local repo to App Store Connect readiness, upload, TestFlight, App Review submission/resubmission, or review issue triage, including signing, metadata, privacy, icons, screenshots, subscriptions, and release evidence.
Orchestrate iOS screenshot automation with xcodebuild/simctl, AXe plans, Koubou framing, review artifacts, and `asc screenshots` upload.
Use when the requested App Store artifact is What's New release notes or promotional text, drafted from git history, bullets, or free text and optionally localized. Not for full listing translation, canonical metadata field sync, or subscription/IAP display names.
Answer App Store release go/no-go questions and choose the next focused release skill. Use for readiness planning, first-submission blockers, release sequencing, or deciding whether to stage or submit; use appstore-review-readiness for concrete validate, submit, monitor, cancel, and repair commands.
Reconcile App Store Connect subscriptions/IAPs with RevenueCat products, entitlements, offerings, and packages using `asc` plus RevenueCat MCP. Use for catalog bootstrap, drift audits, and deterministic product mapping.
Resize, strip alpha, color-convert, validate, and upload App Store screenshots using current `asc screenshots` size data and macOS `sips`.
Validate App Store submission readiness and execute prepared review actions with current `asc` commands. Use after appstore-release-planner chooses the review path, or when the user directly asks to validate, stage, submit, monitor, cancel, or repair ASC review blockers.
Set up App Store Connect bundle IDs, capabilities, certificates, provisioning profiles, local profile install, and encrypted signing sync with `asc`.
Claude Skills — questions
Answers built from the skills we actually parsed.