Langfuse production trace를 관찰하고 품질 regression·비용 이상·실패 패턴을 자동 분석한 뒤 prompt·skill 수정안을 PR draft 형태로 제안한다.
Score 80/100
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR.
Score 80/100
Use when the user wants to brainstorm and refine developer-experience, documentation, or tooling UX work through a "serene DX" aesthetic lens — three fixed variants that sweep…
Score 80/100
Session parking lot — automatically parks diverging ideas and unanswered questions to project-scoped memory; /session resume shows pending items, /session archive closes them,…
Score 80/100
Configure an agent's settings in the current AIM session. Use when the user runs /aim:set.
Score 80/100
Manage .design/config.json settings. Subcommands: profile, parallelism, cleanup, show.
Score 80/100
Plan the UX and UI for a feature before writing code. Runs a structured discovery interview, then produces a design brief that guides implementation.
Score 80/100
Shares knowledge across projects by copying to shared-knowledge directory with cross-project metadata.
Score 80/100
Construct novelty probes that distinguish genuine situated reasoning from pattern-matching. Builds examination scenarios where routine execution fails but interpretation succeeds.
Score 80/100
Professional SEO audit — single page (with argument) or full technical + on-page site audit (no argument)
Score 80/100
Auto-generate CHANGELOG.md from git history — Keep a Changelog format, grouped and categorized
Score 80/100
Generate or update documentation from code — README, API docs, component docs, or single file documentation
Score 80/100
Complete market study for a product/niche — demand analysis, competition audit, keyword volumes, monetization strategy, GO/NO-GO verdict with structured report
Score 80/100
Prepare and route a document for e-signature — run a pre-signature checklist, configure signing order, and send for execution.
Score 80/100
Six hats, thinking hats, explore all perspectives, de Bono. Analyze from multiple perspectives via Six Thinking Hats: Blue (process), White (data), Green (creativity), Yellow…
Score 80/100
Walk through sketches, pick winner + rationale, group by design area, write project skills to ./.claude/skills/design-
-conventions.md.
Score 80/100
Tracks skill usage patterns, edit frequency, and success rates to suggest improvements and optimizations.
Score 80/100
**GUIDE SKILL** — Guide to the Skill Manager for Copilot extension. USE FOR: adding/removing skill repos, syncing skills, pushing feedback, configuring sync intervals,…
Score 80/100
基于文档的项目控制系统，让任何 AI 智能体或人类仅通过读取文件就能恢复项目工作状态——无需外部记忆。当用户需要管理长期项目、跨 session 追踪进度、context 丢失后恢复状态、多智能体协作、审计项目文档健康状况、或避免忘记上次做到哪里时，应使用本 skill。触发场景：'/doc-harness init' 与 '/doc-harness…
Score 80/100
Process unhandled Slack messages as Claudicle with persistent memory. Loads user models and soul state, posts terminal-styled thinking messages, generates cognitive-step…
Score 80/100
AUTO-TRIGGER: Apply this skill when the user is managing a small team of two to six direct reports in a marketing, demand gen, or RevOps function.
Score 80/100
数据分析员工（Data Analyst Agent）的唯一总入口：凡与数据资产、取数、指标、表/视图、 治理职责、知识网络等相关的问题，必须先经本 skill 做编排与路由，再进入找表或问数等子流程。 当用户提出数据类问题、需要知识网络选择、或需要在找表与问数之间切换时使用。
Score 80/100
Claude Code plugin to capture screenshots of web pages, components, and extract site assets as optimized PNG+WebP.
Score 80/100
Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.
Score 80/100
Multi-language SOLID detection rules. Project type detection, interface locations, file size limits per language.
Score 80/100
Run the SPARC Specification phase — gather requirements, define acceptance criteria, identify constraints, and store the spec in memory
Score 80/100
Vocalize Claude's last response using local Qwen3-TTS. Default voice is the Oracle (deep, resonant Dune narrator). Use --preset for emotion-controlled preset speakers.
Score 80/100
Add specs, conventions, constraints, or learnings to project guidelines interactively or automatically
Score 80/100
Initialize project-level state and configure specs via interactive questionnaire.
Score 80/100
Write the full patent specification from claims and invention disclosure. Use when user says \"撰写说明书\", \"write specification\", \"写说明书\", \"patent description\", or wants to…
Score 80/100
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
Score 80/100
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
Score 80/100
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
Score 80/100
Execute the implementation plan by processing and executing all tasks defined in tasks.md
Score 80/100
Execute the implementation planning workflow using the plan template to generate design artifacts.
Score 80/100
Create or update the feature specification from a natural language feature description.
Score 80/100
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
Score 80/100
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
Score 80/100
Execute a batch of backlog tickets in parallel. Use when the user wants to build multiple unblocked tickets simultaneously with integrated QA review.
Score 80/100
Generate game sprites, SVG characters, ASCII art, animated mascots, and isometric turnarounds from images or descriptions.
Score 80/100
Long-running pattern for letting a user steer a multi-cycle agent process via email. Each invocation checks the user-control mailbox for new commands, parses them, applies state…
Score 80/100
Search LinkedIn for remote job opportunities matching the user's resume and apply via Easy Apply. Use when the user wants to find jobs, apply to jobs, or do a job search on…
Score 80/100
Generate a standup update from recent activity. Use when preparing for daily standup, summarizing yesterday's commits and PRs and ticket moves, formatting work into…
Score 80/100
Execute a work plan using Atlas orchestration with agent teams. Reads plan from .sisyphus/plans/, creates a team, spawns specialized teammates to execute tasks in parallel waves.
Score 80/100
Guided workflow for establishing team identity, boundaries, and strategic clarity. Use when starting a new role, inheriting ambiguity, when a team lacks clear identity, or when…
Score 80/100
Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X…
Score 80/100
Adversarially stress-test a technical plan by verifying claims against real docs, running POC code, and updating the plan before you build.
Score 80/100
AIDLC Inception 시작 시 자유 형식 발화 대신 구조화된 템플릿으로 프로젝트 정보를 수집한다. project-info 템플릿과 requirements 템플릿을 순차 생성하여 후속 workspace-detection·requirements-analysis·user-stories skill이 소비할 단일 진실원을…
Score 80/100
Receives CSS and HTML changes made in CSS Studio via MCP and applies them to source code.
Score 80/100
Generate a component handoff doc (.design/DESIGN-STYLE-[ComponentName].md) from existing pipeline artifacts or source files.
Score 80/100
Prevents premature execution on ambiguous requests. Analyzes request clarity using 5W1H decomposition, surfaces hidden assumptions, and generates structured clarifying questions…
Score 80/100
Generate probability-weighted alternative options that challenge default thinking. Forces unconventional alternatives and exposes hidden assumptions behind the "obvious" choice.
Score 80/100
Exposes Claude's reasoning chain as an auditable, decomposable artifact. Quick mode (default) gives assumption inventory + weakest-link in 2 stages.
Score 80/100
Use when the user wants to view or change claudebase settings like global sync, agent skills sync, auto-push, or machine ID.
Score 80/100
Synchronizes harness documentation (CLAUDE.md, harness.md) and install script (harness.sh) with the actual state of .claude/ subdirectories (skills, agents, hooks).
Score 80/100
Use when the user wants to list, create, switch, delete, compare, or inspect config sync profiles.
Score 80/100
Use when the user wants to restore, download, or pull their Claude Code config from GitHub onto this machine.
Score 80/100
Use when the user wants to back up, save, or push their current Claude Code config to GitHub.
Score 80/100
Use when the user wants to set up config sync for the first time, connect to GitHub, or re-initialize the backup repo.
Score 80/100
Walk through every cost and revenue assumption in your business model using structured checklists. Surfaces hidden risks, flags unknowns, and builds a complete assumptions map.
Score 80/100