Loading...
Loading...
Found 202 Skills
Comprehensive evaluation of potential stock investments combining valuation analysis, fundamental research, technical assessment, and clear buy/hold/sell recommendations. Use when the user asks about buying a stock, evaluating investment opportunities, analyzing watchlist candidates, or requests stock recommendations. Provides specific entry prices, position sizing, and conviction ratings.
Buffett-style stock screener — "What would Buffett buy now?" Generates 3–5 candidate stocks from a market / sector / preference query via a two-layer model: hard quant filter (ROE 5y ≥15%, debt/asset ≤50%, FCF positive 3y, listed ≥5y, gross margin ≥30%) → qualitative moat scoring (moat 35% / capital allocation 20% / earnings predictability 20% / valuation 15% / runway 10%). Longbridge CLI first, MCP fallback, WebSearch for gaps only. Output: candidate cards with moat-type tag, quantitative highlights, verdict (🟢 likely buy / 🟡 wait for price / 🔴 not at this price), deep-dive CTA to `longbridge-buffett-moat-analyzer`. Mandatory holding-period education + data-source appendix. Disqualifies airlines, pre-revenue biotech, ST, listing<5y. Triggers: "巴菲特会买什么", "巴菲特选股", "巴菲特风格的股票", "护城河选股", "宽护城河股票", "价值投资选股", "10年不动的股票", "定价权强的公司", "巴菲特會買什麼", "巴菲特選股", "護城河選股", "寬護城河股票", "Buffett screener", "what would Buffett buy", "wide-moat screener", "quality compounder screen", "Berkshire-style screen", "pricing-power screen".
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
Final pass for rhythm, word choice, consistency, and a candid assessment of the finished piece
Fill out job application form fields with context-aware, tailored answers drawn from the candidate's CV and the job description
Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.
Manage local Codex session transcripts, including listing candidate sessions, exporting full or selected sessions to organized Markdown, inspecting archived sessions, and summarizing tool-call history. Use when the user asks to scan, parse, archive, inspect, recover, summarize, manage, or convert Codex sessions, `~/.codex/sessions` data, `~/.codex/archived_sessions` data, `.jsonl` transcripts, tool-call history, or hard-to-read Codex conversation logs.
Analyze code complexity, cyclomatic complexity, maintainability index, and code churn using metrics tools. Use when assessing code quality, identifying refactoring candidates, or monitoring technical debt.
Generate ultra-compact commit messages. Follows the Conventional Commits format with subject ≤50 characters, prioritizing "why" over "what". Supports both Japanese and English. Trigger with "Make a commit message", "/commit", or "/genshijin-commit". Auto-trigger candidate when staging changes.
Mine Claude Code session logs for skill idea candidates. Use when running the weekly skill generation pipeline to extract, score, and backlog new skill ideas from recent coding sessions.
Generate opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, paid newsletters, opinion essays, reported features, technical deep-dives. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including making a flat intro punchier or rewriting a draft opening. Also trigger when user asks for a post title, titre d'article, headline, or when ghostwriting skills reach the opening or titling step. Proposes 3-4 hooks pulling distinct psychological levers (curiosity gap, contrarian, scene, promise, authority), 2 candidates each, waits for the user to pick. Do NOT trigger for social posts (LinkedIn feed, Twitter/X, TikTok, Bluesky, Threads), READMEs or doc first lines, taglines, email subjects or openers, ad copy (Google/Meta Ads), landing-page headlines, press releases, SEO meta, fiction openings, talk/podcast/video script intros, or body rewrites.
Executes full-project QA like a real user by discovering the repository verification and E2E contracts, running build, lint, test, and startup commands, exercising core workflows end-to-end through CLI, HTTP, and browser interfaces, requiring automated regression coverage for supported critical flows, fixing root-cause regressions, and rerunning the full gate. Uses the agent-browser companion skill for Web UI validation when a web surface exists. Use when validating a branch, release candidate, migration, refactor, or risky commit. Do not use for static code review only, one-off unit test edits, planning test cases, or architecture brainstorming without execution — use qa-report for planning and documentation.