Menu
SkillsMP a collecté 73 skills depuis lilpacy/dotfiles. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 73.
Compare an installed package, its release archive, and its source repository; distinguish source drift from runtime state; and backport verified installed-only fixes. Use when installed files or a ZIP were edited directly, or when the repository may be stale.
Langue du texte source : anglais
Maintain product, architecture, design, API, data, and operational documentation in an established repository. Use when deciding whether to edit an existing source of truth or add a document, separating current-state contracts from implementation plans,…
Langue du texte source : anglais
Design, implement, and review CI test-result parsers, PR comments, job summaries, artifacts, and required checks. Use when cancelled or timed-out runs are misreported as test failures, setup/global errors disappear because zero tests ran, diagnostics may…
Langue du texte source : anglais
Locate, identify, and safely summarize prior local Codex conversations from session JSONL when a user asks whether an earlier task, decision, or implementation can be recovered.
Langue du texte source : anglais
Investigate GitHub Actions runtime regressions by comparing recent runs, job and step durations, test counts, slow files, exact-SHA repeats, and critical-path effects. Use when CI or E2E feels slower, a suspected cause needs falsification, or optimization…
Langue du texte source : anglais
Diagnose and fix Playwright tests where a lazy per-test fixture is created after a beforeEach navigation, leaving the page with stale source data. Use when DB fixture prechecks pass but the browser cannot find the created entity.
Langue du texte source : anglais
Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and…
Langue du texte source : anglais
Integrate a new or migrated UI into an established product so its layout, surfaces, states, and interactions feel native without coupling unrelated domain logic. Use when a page looks stylistically different from neighboring workflows, when deciding what…
Langue du texte source : anglais
Diagnose, build, and verify local authentication environments that use third-party identity providers, custom local domains, nonstandard ports, or concurrent worktrees. Use when login callbacks or logout redirects reach the wrong origin, provider URL…
Langue du texte source : anglais
Orchestrates a gated, dialogue-driven interaction-design review from verified business understanding through decision requirements, target value loops, decision specifications, design principles, contradiction checks, state machines, information architecture,…
Langue du texte source : japonais
Classify specification-derived verification points into the smallest reliable test layers before implementing or changing behavior, then reclassify them from actual test evidence before adding system or E2E coverage. Use for feature work, behavior changes,…
Langue du texte source : anglais
Measure and fix perceived tooltip latency in browser UIs. Use when a tooltip technically appears but users report that hover or focus feedback is slow, inconsistent, or unresponsive, or when reviewing a tooltip timing change with Playwright.
Langue du texte source : anglais
Add and verify cross-platform browser notifications and default completion sounds for long-running web jobs. Use when a web UI should alert users after generation, export, rendering, uploads, or other asynchronous work finishes.
Langue du texte source : anglais
Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals,…
Langue du texte source : anglais
Diagnose why a site is missing or underperforming in branded search after a domain or hostname migration. Use when checking old-to-new redirects, HTTP/HTTPS canonicalization, robots directives, sitemaps, on-page brand signals, structured data, Search Console…
Langue du texte source : anglais
ユーザー向けの回答、要件整理、説明、計画、レビュー、仕様、要約を作成するときに使う。自然言語だけでは条件、状態、多重度、期間、時刻、境界値、制約、推論、計算が曖昧になりうる場合、表、デシジョンテーブル、Mermaid 図、計算式、境界値表で一意化する。推測で補った図表要素は必ず明示する。
Langue du texte source : japonais
Collaboratively review GitHub pull requests, verify a user's understanding through a no-post question-by-question walkthrough, or post only user-approved inline comments, suggestions, and review summaries through gh. Use whenever an agent is asked to review…
Langue du texte source : anglais
Safely turn a local source directory or release archive into a new private GitHub repository, with secret scanning before commit and across Git history, privacy-preserving commit metadata, release-archive verification, and post-push visibility checks.
Langue du texte source : anglais
Ingest a completed agent conversation into an LLM Wiki repository that uses queries, Knowledge Deltas, Summaries, Entities, index.md, and log.md. Use when a user explicitly asks to ingest or add the current query/conversation to the wiki, especially in…
Langue du texte source : anglais
Resolve Git pulls blocked because a running editor, sync client, metadata plugin, formatter, or other file watcher recreates local changes immediately after `git stash`. Use when a pull reports that local changes would be overwritten, a normal stash appears…
Langue du texte source : anglais
Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...', 'Actually...'), (2) User requests a capability that doesn't exist, (3) Claude realizes its knowledge is…
Langue du texte source : anglais
Use before presenting implementation plans and after non-trivial commits that require review. Runs codex exec in read-only review mode, handles resume, MCP transport errors, and review timeout semantics.
Langue du texte source : anglais
Use only when the user explicitly asks for Fable/Claude review. Runs claude -p in streaming review mode with the configured Fable model, constrains tools for read-only review plus currentness checks, handles resume, and defines review timeout semantics.
Langue du texte source : anglais
Cross-agent messaging via SQLite. Send messages between Claude Code, Codex, Gemini CLI, and other agents. No daemon, no network, no dependencies beyond bash and sqlite3.
Langue du texte source : anglais
Reclassify existing Claude Code subagents and skills, then migrate files into the appropriate structure with backups and a report.
Langue du texte source : anglais
Claude Code に MCP サーバーを追加・削除・一覧・確認するためのセットアップ手順を実行する。
Langue du texte source : japonais
Generate a compact skills index from a skills directory for use in AGENTS.md and related agent instructions.
Langue du texte source : japonais
課題に関連する専門語彙や隣接語彙を探索し、次の調査クエリへ落とし込む語彙コーチ。
Langue du texte source : japonais
lilpacyのスタイルで技術記事を執筆・レビュー・改善する
Langue du texte source : japonais
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
Langue du texte source : anglais
Delegate coding tasks to Codex (gpt-5.3-codex-spark) via `codex exec` while acting as PM: write work-order prompts, dispatch, verify results from the working tree, and iterate with `codex exec resume`.
Langue du texte source : anglais
Delegate coding tasks to Cursor IDE's Composer agent via the macOS Accessibility API (cursor-compose) while acting as PM: write specs, dispatch prompts, then verify results from the working tree.
Langue du texte source : anglais
Read X/Twitter status posts and X Articles. Use `npx curl.md` for public status URLs, and use chrome-devtools-mcp with the logged-in headed `x-for-ai` Chrome profile for x.com article URLs that require authentication. Trigger when the user asks to view,…
Langue du texte source : anglais
Use when committing, pushing, or preparing PRs. Defines the user's commit workflow, message style discovery, review handoff, and branch/worktree push requirements.
Langue du texte source : anglais
Linearのissueを整理し、会話しながら新規issueに落とすスキル。2つのモードを持つ: (1) 既存issue整理: Backlogの全issueをINVEST原則で診断し、分割・統合・再分類を提案・実行 (2) 会話→issue化: ユーザーとの対話から要件を引き出し、適切な粒度のissueに落とす 両モード完了後、整理された実行計画を自動生成する。 トリガー: 「issueを整理して」「Backlog整理」「issue棚卸し」「やること整理」「実行計画を作って」…
Langue du texte source : japonais
Use for code implementation, bug fixes, refactors, and test additions. Enforces the user's development style: YAGNI, TDD, clear contracts, separation of concerns, no unsolicited fallback or backward-compatibility helpers, and maintainable code structure.
Langue du texte source : anglais
Use when writing or editing tests. Tests should be ordered by near-normal, normal, then abnormal cases where applicable, and test names must be Japanese behavior descriptions from a reviewer/user perspective.
Langue du texte source : anglais
Use when searching the web or reading online documentation. Prefer DuckDuckGo for search and read documents through npx curl.md instead of raw HTML.
Langue du texte source : anglais
Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.
Langue du texte source : anglais
GoF/オブジェクト指向デザインパターンを関数型プログラミング（pure functions, higher-order functions, ADT, composition, immutability, effect boundaries）でシンプルに整理・設計・リファクタリングする。Strategy/Factory/Adapter/ObserverなどGoF全23パターンのFP置き換え、適用判断、具体事例を提示する必要があるときに使う。
Langue du texte source : japonais