Навыков: 28 594. Сортировка по числу звёзд.
Surface deepening refactors that turn shallow modules into deep ones, informed by `CONTEXT.md` and `docs/adr/`. Use when...
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by...
Explore a codebase using qualitative exploration plus quantitative metrics, surface architectural friction, discover tes...
Guide for improving the Auctionet extension over time — adding quality rules, tuning AI prompts, improving cataloging ac...
Find and implement a valid quick-win improvement to codebase hygiene in the current project. Use when the user asks to i...
Analyzes prompts and produces improved versions using Anthropic's prompt engineering best practices. Use when asked to i...
Analyse l'historique local des conversations Claude Code (fichiers .jsonl sous ~/.claude/projects/) pour repérer les cor...
Find and implement a valid quick-win improvement to the quality of preexisting tests in the current project. Use when th...
Coordinate sequential improvement stages (analyze → propose → build → validate) with Prompt Architect clarity and Skill...
Expert at automatically applying improvements to Claude Code components based on quality analysis. Enhances descriptions...
Grant the imsg CLI its macOS privacy permissions (Full Disk Access, Automation → Messages, Contacts) and prove each one...
Use when writing or reviewing in-code comments. Explains the 'why not how' standard.
Set a boundary with in-laws or extended family kindly and clearly — the words to say, a united-front approach with your...
Maintainer-only. Use when triaging inbound GitHub issues and pull requests on skyf0xx/hedgehog — "triage the issues", "c...
Email triage system that handles both one-time setup and recurring triage in a single skill. Auto-detects state: if no k...
Show every item across managed projects needing the user's attention — PRs, assigned issues, comments, blockers.
One-time setup skill that builds a personalized inbox triage knowledge base via interactive interview. Interviews the us...
Comprehensive incident response framework from detection through resolution and post-incident review. Battle-tested SRE/...
Write a structured incident postmortem or post-incident review. Use when asked to write a postmortem, incident report, P...
Build a blameless, cited postmortem timeline and document skeleton from a saved incident issue export, ordering label ch...
IR playbook execution — evidence collection, timeline analysis, memory forensics, disk forensics, containment strategies...
Production-ready templates for incident response runbooks covering detection, triage, mitigation, resolution, and commun...
Fix MSBuild targets that generate files during the build but those files are missing from compilation or output. USE FOR...
Fix MSBuild targets that generate files during the build but those files are missing from compilation or output. Only ac...
Build confidential dApps on Solana using Inco Lightning encryption — encrypted balances, private transfers, and attested...
Assess incomplete onboardings using COLD/WARM/HOT temperature model with time decay
Find and implement a valid quick-win testing coverage improvement in the current project. Use when the user asks to incr...
Smart work continuation system that detects implementation intent and routes to active increment or creates new one. Act...
Guide for optimizing MSBuild incremental builds. USE FOR: builds slower than expected on subsequent runs, 'nothing chang...
Guide for optimizing MSBuild incremental builds. Only activate in MSBuild/.NET build context. USE FOR: builds slower tha...
Build in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over com...
Commit boundaries and messages on a task branch. Use when deciding where to cut a commit or how to word one while implem...
Use when entering a large unfamiliar codebase. Build understanding in layers, not all-at-once.
Guidelines for incremental development practices. Claude should use this skill when writing multiple similar files (test...
Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amou...
Use when .forge/tasks.yaml exists and implementation is starting, when executing a planned task list one task at a time,...
Breaks changes into thin vertical slices. Start with a minimal end-to-end slice, then add layers. Prevents massive diffs...
Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that f...
Comprehensive guide for implementing code incrementally following established patterns, conventions, and quality standar...
Build features in small, verifiable steps with continuous test validation. Use when implementing any feature from a plan...
Decompose a large or risky change into a sequence of independently safe intermediate states, so the system stays green a...
Use when implementing features or refactoring with TDD - enforces writing ONE test at a time, implementing minimal code...
Scrape job listings from Indeed.com by keyword, location, and country. Returns job title, company, salary, rating, descr...
独立开发者与微型 SaaS — 单人或极小团队 (≤3 人) 构建可持续订阅收入的软件产品商业, 有别于自由职业/咨询、企业级 SaaS 和开源维护: (a) 产品发现与验证 (自己的痒 vs 市场优先 Nugent/Walling; 着陆...
Control Adobe InDesign from the shell via Flue - ExtendScript bridges without an MCP server.
Build or refresh the Operator Project Index.
Build or refresh the codemunch symbol index for the current project. Walks every source file, extracts all symbols (func...
代码索引(.fe-index/)的统一查询入口:按代码路径自动判定该查前端页面索引还是后端模块索引,给出新鲜度校验与查询入口;无索引自动降级。触发:"查索引"、"这段代码有索引吗"、"改这个要查哪个索引"、"index lookup"。