Loading...
Loading...
Found 160 Skills
Analyze, prioritize, and document test cases in TMS (Jira/Xray) -- the bridge between manual QA and test automation. Use when creating Test/ATP/ATR artifacts, calculating ROI to choose which tests to automate, maintaining US-ATP-ATR-TC traceability, or repairing broken TMS links. Supports four scopes: module-driven (exhaustive module exploration), ticket-driven (QA-approved user story), bug-driven (regression TC for a closed bug), and ad-hoc/exploratory. Produces three outcomes per TC: Candidate (feeds test-automation), Manual (terminal), Deferred (terminal). Triggers on: document tests, create test cases in Jira/Xray, prioritize for automation, ROI analysis, which tests to automate, Candidate vs Manual, link ATP to ATR, fix TMS traceability, stage 4, turn this bug into a regression test. Do NOT use for writing test code (test-automation) or running suites (regression-testing).
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".
Convert noisy GitHub repository search results into recommendation-grade candidate lists with explicit metadata, freshness, traction signal, provenance labels, and rollback-safe reporting for maintenance PR workflows.
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.
Use this skill when writing job descriptions, building sourcing strategies, designing screening processes, or creating interview frameworks. Triggers on job descriptions, candidate sourcing, screening criteria, interview loops, recruiting pipelines, offer management, and any task requiring talent acquisition process design.
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.
Match spoken edit beats to candidate B-roll assets using a normalized transcript, subtitle chunking, optional A-roll analysis, and a reusable B-roll catalog. Use this when the goal is to decide what B-roll should support each beat, not just to list assets or describe the video.
Identify candidate stocks with sufficient pullbacks but intact trends and acceptable support structures, and output observation ranges, reversal signals, and invalidation conditions. Suitable for scenarios such as bargain-hunting opportunity screening, secondary entry for strong stocks, and pullback observation for trend stocks.
Use this when the user wants to post a daily X/Twitter tweet inspired by one of their recently published WeChat Official Account articles. It selects the newest article that hasn't been tweeted yet, drafts 3 tweet candidates from it (from different angles — quote / metaphor / one-liner), posts the selected one via xurl, and records the action to history. Triggers — "Post a daily tweet", "Tweet from an article", "Today's tweet", "/wjs-tweeting-from-articles".
Executes full-project QA like a real user by discovering the repository verification contract, running build, lint, test, and startup commands, exercising core workflows end-to-end, creating realistic fixtures when needed, fixing root-cause regressions, and rerunning the full gate. 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, or architecture brainstorming without execution.
Use this skill to translate a classifier's in-place verdict into a precise, page-by-page work plan for the docs-sync panel. Activate after docs-impact-classifier returns verdict in_place; reads the candidate page list, fetches the actual page contents, narrows scope to specific sections within each page, and emits the per-page task brief the panel fans out against.
Analyze candidate algorithms for time/space complexity, scalability limits, and resource-budget fit (CPU, memory, I/O, concurrency). Use when feasibility depends on input growth or latency/memory constraints and quantitative bounds are required before implementation; do not use for persistence schema or deployment topology decisions.