atuin-memory
Check, store, and retrieve atuin memory for project roadmap, feature work, and optional cross-project priming context.
reduce-orchestrator
MapReduce root/orchestrator with a mandatory parallel Verify phase, narrative-first reduction, deterministic artifact lifecycle management (.rlm run/archives), and concurrency safety (per-run locks + cleanup lock). Use when coordinating many parallel map-worker tasks under optional hint_paths, then synthesizing narrative reports into a decision to iterate or finish.
map-worker
Contract-based MapReduce worker for executing a task (may be broad) under optional hint_paths, producing a narrative report. Use when an orchestrator invokes a map worker (llm_query role) many times in parallel and needs mergeable narrative reports.
cli-ninja
Master CLI navigation and code exploration using modern command-line tools. Use this skill when navigating repositories, searching for files/text/code patterns, or working with structured data (JSON/YAML/XML). Provides guidance on fd (file finding), rg (text search), ast-grep (code structure), fzf (interactive selection), jq (JSON), and yq (YAML/XML).
task-debugger
Debug and fix Taskcluster task failures
image-compress
对图片进行智能压缩优化。支持本地路径、文件夹和远程 URL，直传 NX API 压缩后返回 CDN 地址和压缩率。适用于用户提到图片压缩、图片优化、减小图片体积、TinyPNG、JPG/PNG/BMP/WebP/TGA 压缩的场景。
hug-worktree
Use whenever starting branch-worthy work (features, bugfixes, refactors, spec/plan documents, multi-step tasks) — the worktree-first ritual.
Hug SCM Repository Analysis
Expert-level Git repository investigation using Hug SCM tools for understanding code evolution, tracking down bugs, analyzing changes, and managing development workflows
hug-workflow
|
code-reviewer
审查代码，以了解最佳实践和潜在问题。可用于代码审查、检查 PR 或分析代码质量。
pr-creator
创建 Git Pull Request 的专业技能。自动化 PR 创建流程，包括分支管理、更改分析和 PR 描述生成。
skill-creator
创建有效技能的指南。当用户想要创建新技能（或更新现有技能）以通过专业知识、工作流程或工具集成扩展 Claude 功能时，应使用此技能。
git-commit
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
rhetorical-analysis
Analyse rhétorique et épistémologique d'articles, discours et textes argumentatifs. Utiliser ce skill quand l'utilisateur demande d'analyser la qualité argumentative d'un texte, d'identifier des sophismes ou biais, d'évaluer la fiabilité des sources citées, de déconstruire la logique d'un raisonnement, ou de produire une réécriture critique structurée d'un document.
ai-image-asset-generator
This skill should be used when generating AI image assets for websites, landing pages, or applications. It automatically analyzes page requirements, generates images using Gemini API, removes backgrounds, converts to SVG for interactivity, and places assets in frontend code. Ideal for creating hero images, icons, backgrounds, product mockups, and infographic elements. Use this skill when users need image assets for their web projects.
docker-containerization
This skill should be used when containerizing applications with Docker, creating Dockerfiles, docker-compose configurations, or deploying containers to various platforms. Ideal for Next.js, React, Node.js applications requiring containerization for development, production, or CI/CD pipelines. Use this skill when users need Docker configurations, multi-stage builds, container orchestration, or deployment to Kubernetes, ECS, Cloud Run, etc.
serr-structured-error-wrapper
Serr allows us to enrich our Go application errors with location, etc, and bubble them up to the caller where we only have to log once
flowerpower
Create and manage data pipelines using the FlowerPower framework with Hamilton DAGs and uv. Use when users request creating flowerpower projects, pipelines, Hamilton dataflows, or ask about flowerpower configuration, execution, or CLI commands.
sparze
Expert guidance for Sparze ECS apps including systems, queries, components, resources, events, and performance trade-offs.
nx-matting
使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除，并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片，或 MP4/MOV/WebM 视频的场景；无需 Python、PyTorch 或 CUDA。
foop-use-maintain
MUST USE when FINDING, EXECUTING, UPDATING, BACKBURNERING, or CANCELLING existing FOOPs (Foolish Optimization Process). Covers: listing/finding FOOPs in chronological order (little-endian ls|rev|sort -V|rev, foop_check.py list/get_last/check), the two-file system (must read both spec and plan before executing), status lifecycle (Draft→Brewing→Final→Implementing→complete), plan execution flow (begin→worktree→all-work-in-worktree→commit-regularly→merge), checkbox lifecycle (completing with timestamp, backburnering with [x] backburnered, cancelling with [x] Canceled + [-] per-item), worktree execution (create from jia, work only in worktree, merge to jia, cleanup), sub-task execution patterns (parent not checked until children done, the merge STOP pattern, conflict repair because Foolish uses merge not rebase), comprehensive test verification, human communication protocol (PTAL reminder with FOOP number and worktree path), and safety invariants. Gives exact copy-pasteable commands with <NUMBER> and <SHORT_DESCRIPTION> placeholders. Triggers: 'find foop', 'list foop', 'execute foop', 'foop status', 'foop execution', 'check foop checkbox', 'backburner foop', 'cancel foop', 'deprecate foop', 'foop merge', 'foop cleanup', 'foop worktree', 'foop begun', 'foop progress', 'resume foop', 'foop PTAL'.
foolish-debugging
MUST USE for debugging Foolish FVM/FIR behavior — wrong brane evaluation, unexpected NK/ECONSTANIC, search resolution failures, NYES state machine bugs, name-lookup errors. The Foolish VM has no interactive debugger; debugging is unit-test-driven: write a temporary test that reproduces the issue, step the FVM to the offending line, inspect FIR NYES state and query the FVM via ib_search/ab_search, then promote the test to a regression test or delete it. This skill gives the exact Rust API and copy-pasteable templates. Triggers: 'debug Foolish', 'FVM bug', 'NYES wrong', 'brane not resolving', 'search returns NK', 'ib_search', 'ab_search', 'why is my brane NK', 'FIR state', 'step the FVM', 'foolish unit test debug', 'temporary_reproduce_to_debug'.
foop-write-plan
MUST USE when CREATING or PLANNING a FOOP (Foolish Optimization Process) — writing the specification file (FOOP-#.md) and the plan file (FOOP-#.plan.md). Covers: what a FOOP is, the two-file system (spec + plan), little-endian numbering (FOOP-1→FOOP-9→FOOP-01→FOOP-11→FOOP-21...), the foop_check.py helper script (check/get_last/gen_next/list), naming convention (dash in filenames, space in prose), the spec template (frontmatter fields foop/title/status/phase/begun, body sections Abstract/Motivation/Specification/FIR Impact/UBC Step Impact/Test Plan/Rejected Alternatives/Open Questions/References), the D-prefix sort-key rule, plan construction rules (ordered/concrete/trackable, worktree lifecycle checkboxes, sub-tasks, variable expansion), checkbox format (timestamp on next indented line), sub-task splitting, worktree branch tracking (naming, creation, lifecycle checkboxes), comprehensive snapshot tests (foop_<NUMBER>_comprehensive.foo), and the minimal plan skeleton. Gives exact copy-pasteable commands with <NUMBER> and <SHORT_DESCRIPTION> placeholders. Triggers: 'create foop', 'new foop', 'write foop', 'foop spec', 'foop plan', 'foop template', 'foop numbering', 'foop frontmatter', 'foop_check gen_next', 'plan a foop', 'foop worktree setup', 'foop comprehensive test'.
testing-automation
Testing patterns with Bun test runner, coverage thresholds, mocking, and CI/CD integration. Use when writing tests, organizing test files, or setting up quality gates.
cli-development
CLI development patterns with Commander.js, argument parsing, and user experience best practices. Use when creating commands, handling options, formatting output, or building CLI tools.
bun-development
Bun build system, development workflow, and TypeScript patterns. Use when working with Bun projects, setting up development environment, or managing dependencies with Bun package manager.
git-automation
Automate Git workflows with atomic commits, Beads integration, and real-time sync. Use when managing Git commits, branches, task tracking, or handling complex multi-file changes with proper validation.
subagent-coordination
Multi-agent coordination patterns for delegating work between specialized agents, managing agent roles, and orchestrating workflows across multiple AI agents.
security-scanning
Security scanning with dependency audits, secret detection, static analysis, and vulnerability management. Use when checking for vulnerabilities, scanning dependencies, or enforcing security gates.
release-publishing
Release workflow with changesets, version bumping, changelog generation, and npm publishing. Use when preparing releases, managing versions, or publishing to npm.
library-research
Research library documentation and API references using Context7 integration. Use when users ask about libraries, frameworks, packages, APIs, or need documentation for third-party code.
liaison-workflows
Task management and workflow patterns using liaison. Use when managing tasks, creating workflows, or working with task-driven automation.
logging-tracer
Use when the user asks to "add logging", "add tracing", "improve observability", "OpenTelemetry", "structured logging", or reports silent failures or no runtime visibility. Generates stack-appropriate logging with optional OTel.
debug-loop
Use for deep iterative debugging when memory lookup returns LIKELY_MATCH/WEAK_SIGNAL/NO_MATCH, a fix didn't hold, or the user asks for root cause analysis. Not for known fixes or trivial issues.
debugging-memory
Use when the user asks to "debug this", "fix this bug", "investigate error", "diagnose", "root cause", or reports a crash/exception/failure. Memory-first workflow checks past incidents before investigating.
kubernetes-debugger
|
clarify
Ask questions if underspecified. Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
autocli
|
hugo-blog
Self-contained end-to-end blog writing system for hugozhu.site — planning, style enforcement, generation, case study patterns, AI illustration, evaluation, and publishing. Inlines Chinese typography rules and image-generation provider quirks; no external skills required.
catchup-ecc
Use when scanning new commits in the external affaan-m/everything-claude-code repo for ideas worth adopting. Triggers on "catchup ecc", "check ecc", "what is new in ecc", "check affaan".
convene-council
Use when an ambiguous decision has multiple credible paths and needs structured disagreement before choosing. Triggers on "council", "second opinion", "convene council", "decision council", "multiple perspectives", "go or no go".
research
Use when researching a topic via multi-source synthesis (literature review, competitive analysis, tech comparison); for a fact-checked cited web report use deep-research. Triggers on "research this", "investigate", "survey the landscape".
assess-evolution
Use when assessing a project's long-term evolution health and emitting a phased, session-sized PRD roadmap to get it back on track. Triggers on "evolution audit", "assess this project", "health-check the codebase", "what should we refactor".
audit-atlas
Use when auditing the health of Cartographer atlases across all tracked repos. Reports fresh-atlas coverage, staleness distribution, atlas size, and layer population. Triggers on "audit atlas", "atlas health", "cartographer coverage".
audit-echo
Use when reviewing cartographer-echo fire patterns to tune stopwords, threshold false-positives, or surface duplicate-detection trends. Triggers on "audit echo", "echo audit", "duplicate detection report".
brief-portfolio
Use when the user wants a portfolio-wide status brief of all gita-registered repos as a single-file HTML dashboard with actionable follow-ups. Triggers on "brief portfolio", "state of my repos", "repo dashboard", "cross-repo todos".
brush
Use when running a project hygiene pass on a repo - git cleanup, leftover triage, evolution check, backlog review, AGENTS.md refresh. Triggers on "brush", "brush the project", "project hygiene", "git hygiene", "apply git hygiene", "tidy repo", "clean up this repo".
sort-agent-setup
Use when a project needs a trimmed Claude install instead of the full global setup, sorting skills/rules/hooks into DAILY vs LIBRARY with repo evidence. Triggers on "agent sort", "trim skills for repo", "daily vs library", "project install plan".
audit-recon
Use when auditing cartographer recon-brief injections in the audit log. Reports (repo x day) inject uniqueness, missing-atlas repos, stale-at-inject rate, and excerpt-size distribution. Triggers on "audit recon", "recon audit", "recon injections".
design-solution
Use when turning a PRD into a reviewed design doc (the HOW) before planning tasks - architecture fit, exact interfaces, reuse, alternatives, then an autonomous adversarial review. Triggers on "design solution", "design this PRD".
Page 1353 of 1713 · 85634 results
