Skills for Claude Code

These skills are associated with Claude Code because their author either published them under the harness's install path or tagged the repository for it on GitHub. Both are statements of intent by the author.

Neither is a test result. We have not run any of these with and without the skill enabled, so nothing here tells you whether a skill improves output, what it adds in tokens, or whether it duplicates behaviour the harness already has. When we run that comparison, the numbers will appear here with the task, the versions and the budget.

Worked on in the last 90 days (53)

Someone pushed a commit recently. This is the shortlist worth trying first.

fcakyon-claude-codex-settings-hetzner-deploy — last commit 2026-08-06
This skill should be used when user asks to "deploy to Hetzner", "create Hetzner server", "manage Hetzner Cloud", "hcloud CLI", or works wi…
fcakyon-claude-codex-settings-livekit-skills — last commit 2026-08-06
Build voice AI agents with LiveKit Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "…
fcakyon-claude-codex-settings-mongodb-atlas-stream-processing — last commit 2026-08-06
Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle…
fcakyon-claude-codex-settings-mongodb-connection — last commit 2026-08-06
Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working…
fcakyon-claude-codex-settings-mongodb-mcp-setup — last commit 2026-08-06
Guide users through configuring key MongoDB MCP server options. Use this skill when a user has the MongoDB MCP server installed but hasn't…
fcakyon-claude-codex-settings-mongodb-natural-language-querying — last commit 2026-08-06
Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample docume…
fcakyon-claude-codex-settings-openai-frontend-design — last commit 2026-08-06
Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the us…
fcakyon-claude-codex-settings-pdf — last commit 2026-08-06
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining…
fcakyon-claude-codex-settings-pptx — last commit 2026-08-06
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitc…
fcakyon-claude-codex-settings-resolve-pr-comments — last commit 2026-08-06
This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respo…
fcakyon-claude-codex-settings-review-pr — last commit 2026-08-06
This skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this PR", "check PR #N", p…
fcakyon-claude-codex-settings-setup — last commit 2026-08-06
This skill should be used when user encounters "Azure MCP error", "Azure authentication failed", "az login required", "Azure CLI not found"…
fcakyon-claude-codex-settings-setup-8d6e21 — last commit 2026-08-06
This skill should be used when the user asks "how to setup GitHub CLI", "configure gh", "gh auth not working", "GitHub CLI connection faile…
fcakyon-claude-codex-settings-setup-e93720 — last commit 2026-08-06
This skill should be used when user encounters "ADC not found", "gcloud auth error", "GCloud MCP error", "Application Default Credentials",…
fcakyon-claude-codex-settings-update-pr-summary — last commit 2026-08-06
This skill should be used when user asks to "update PR summary", "update PR description", "rewrite PR body", "refresh PR title and body", o…
fcakyon-claude-codex-settings-xlsx — last commit 2026-08-06
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, o…
frappucc1no-recall-loom-recallloom — last commit 2026-08-06
Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state sum…
serejaris-personal-corp-os-art-director — last commit 2026-08-06
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
serejaris-personal-corp-os-cc-analytics — last commit 2026-08-06
Use when user asks for Claude Code usage stats, weekly analytics, project activity summary, or wants to see what projects were worked on. T…
serejaris-personal-corp-os-ceo-council — last commit 2026-08-06
Use when needing strategic project analysis from multiple independent expert perspectives. Triggers on business decisions, growth strategy,…
serejaris-personal-corp-os-claude-md-writer — last commit 2026-08-06
Use when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content organization
serejaris-personal-corp-os-design-minimal — last commit 2026-08-06
Use when the user explicitly asks for a standalone HTML page in a restrained minimal style, especially reading-first dashboards, briefs, ha…
serejaris-personal-corp-os-grill-me — last commit 2026-08-06
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use…
serejaris-personal-corp-os-html-draft — last commit 2026-08-06
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec she…
serejaris-personal-corp-os-meeting-copilot — last commit 2026-08-06
Use when preparing for, running, or closing a live meeting with an AI assistant dashboard. Triggers on "meeting copilot", "live copilot", "…
serejaris-personal-corp-os-paperclip-api — last commit 2026-08-06
Use when managing Paperclip AI agent companies - creating tasks, managing agents, approving hires, running heartbeats, or any Paperclip con…
serejaris-personal-corp-os-parallel-design-variants — last commit 2026-08-06
Use when you want several genuinely different design directions to choose from instead of one design you will iterate on — a page or UI red…
serejaris-personal-corp-os-pm-brainstorm — last commit 2026-08-06
Проводит структурированный сеанс дивергенции вокруг конкретной продуктовой проблемы или возможности. Встроены SCAMPER (7 ракурсов), 5 Whys…
serejaris-personal-corp-os-pm-competitive — last commit 2026-08-06
Готовит многомерный разбор конкурентов — feature-матрица, SWOT с cross-strategy, 5 сил Портера, сравнение ценообразования, позиционирование…
serejaris-personal-corp-os-pm-feedback — last commit 2026-08-06
Классифицирует пользовательский фидбек (Excel/CSV/текст) по 6 категориям, делает sentiment-анализ, кластеризацию тем, анализ трендов, триан…
serejaris-personal-corp-os-pm-metrics — last commit 2026-08-06
Делает ревью продуктовых метрик — тренды, аномалии, root causes и рекомендации к действиям. Включает декомпозицию North Star (L1/L2), диагн…
serejaris-personal-corp-os-pm-prd — last commit 2026-08-06
Генерирует структурированный PRD (Product Requirements Document) с шаблонами под тип продукта (B2C / B2B / внутренний инструмент / платформ…
serejaris-personal-corp-os-pm-prioritize — last commit 2026-08-06
Use when ranking a list of requirements, features, or backlog items using RICE / ICE / MoSCoW / Kano. Built-in decision tree picks the righ…
serejaris-personal-corp-os-pm-roadmap — last commit 2026-08-06
Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате…
serejaris-personal-corp-os-pm-user-stories — last commit 2026-08-06
Разбивает Epic или крупное требование на независимые User Stories с acceptance criteria в формате Given-When-Then, проверкой по INVEST и оц…
serejaris-personal-corp-os-product-data-audit — last commit 2026-08-06
Use when auditing a product, business, or project ecosystem — analyzing data sources, decision loops, bottlenecks, and implementation conto…
serejaris-personal-corp-os-readme-generator — last commit 2026-08-06
Use when creating or rewriting README.md for projects. Triggers on "write README", "create README", "update README". Creates human-focused…
serejaris-personal-corp-os-tg-bot-ops — last commit 2026-08-06
Use when operating, debugging, deploying, or monitoring a Telegram bot or Telegram-to-agent gateway. Triggers on "telegram bot down", "bot…
serejaris-personal-corp-os-to-issues — last commit 2026-08-06
Break a plan, spec, or PRD into independently-grabbable task files using tracer-bullet vertical slices.
serejaris-personal-corp-os-to-prd — last commit 2026-08-06
Turn the current conversation into a PRD file in the project folder — no interview, just synthesis of what you've already discussed.
serejaris-personal-corp-os-weekly-planning — last commit 2026-08-06
Use when transitioning from retro to weekly plan, prioritizing backlog, choosing outcomes for the week, or when user says "план на неделю",…
a5c-ai-babysitter-architecture-patterns — last commit 2026-08-06
System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
a5c-ai-babysitter-assimilate-popular-workflows — last commit 2026-08-06
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repo…
a5c-ai-babysitter-babysit-babysitter-issues — last commit 2026-08-06
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter…
a5c-ai-babysitter-catalog-babysitter-users — last commit 2026-08-06
Discover public GitHub repositories that import defineTask from @a5c-ai/babysitter-sdk and maintain a deduplicated catalog of those reposit…
a5c-ai-babysitter-code-generation — last commit 2026-08-06
Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit to…
a5c-ai-babysitter-code-review-patterns — last commit 2026-08-06
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Ro…
a5c-ai-babysitter-debugging-patterns — last commit 2026-08-06
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scori…
a5c-ai-babysitter-fix-failing-pipelines — last commit 2026-08-06
This skill should be used when the user asks to "fix pipelines", "fix CI", "check staging pipelines", "fix failing workflows", "fix failing…
a5c-ai-babysitter-planning-patterns — last commit 2026-08-06
Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.
a5c-ai-babysitter-process-builder — last commit 2026-08-06
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from…
a5c-ai-babysitter-retrospect-external-babysitter-run — last commit 2026-08-06
For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and perform a…
a5c-ai-babysitter-session-memory — last commit 2026-08-06
Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must l…

Page 6 of 24

How this page is ordered

Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.

Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.