SiyuQian

Use when the agent keeps making the same mistake across multiple PRs, when lint/test failures recur on the same rule, when PR review comments reveal a missing guide or unenforced convention, or when you want to proactively evolve the harness. Triggers on "self-evolve", "optimize harness", "update harness docs", "agent keeps making the same mistake", "harness self evolution", "harness 自我进化", "优化 harness", "更新 harness 文档".

Turn a single article, document, or web page into a standalone HTML learning artifact: either a bilingual digest or a chaptered Chinese study guide with source summaries. MUST use this skill — not raw summarization — whenever the user asks to summarize, digest, get key points from, extract takeaways from, or turn a URL, PDF, .docx, .md, .txt, paper, report, or blog post into notes or study material. Trigger on: summarize this, key points, takeaways, digest, highlights, TL;DR, what does it say, overview, 学习资料, 学习笔记, 复习资料, 总结, 摘要, 要点, 重点, 提取, 整理, 讲了什么. NOT for: writing new content, translating, comparing two documents, building apps, multi-source news, code review, or data/CSV analysis.

Use proactively when harness documentation needs updating — new module/package added, skill created or removed, CLI surface changed, exec plan completed, new convention established, or CLAUDE.md exceeds ~100 lines. Also use when asked to set up AGENTS.md/skills/sub-agents, fix agent drift, or retrofit guardrails.

Use when setting up a repository for autonomous coding agents, adding guardrails, context files, or automation so agents ship reliably without constant review. Triggers on "make this repo agent-friendly", "agents keep drifting", "set up AGENTS.md / skills / sub-agents", "harness engineering", architectural drift with agent-authored code, or retrofitting guardrails after output quality decayed.

Use when the user wants to resolve, fix, work through, or burn down open GitHub issues in a repository — "fix all the issues", "resolve these tickets", "work through the repo-scan issues", "clear the backlog", "fix issue

Use when the user asks to scan, audit, or sweep an entire GitHub repository for issues and file them as tickets — "scan this repo", "audit the codebase", "find bugs/security holes/missing tests", "check the docs are still accurate", "/repo-scan", "open issues for all the problems you find". Scans security, edge cases, testing coverage, and doc/code drift (CLAUDE.md, AGENTS.md, README.md and the docs they link to) without assuming business logic. Do NOT use for reviewing a single PR (use devpilot-pr-review) or language-specific style review (use devpilot-google-go-style).

Use when the user wants to review every pull request currently requesting their review, batch review a review queue, sweep pending PR reviews, or run PR reviews across all review-requested pull requests. Discovers the queue with `devpilot github prs review-queue` and delegates each real review to `devpilot-pr-review`; do not use for reviewing a single specified PR.

Use when the user wants to generate, scaffold, or auto-write end-to-end / browser tests for a web app — "generate e2e tests", "write Playwright tests", "auto-generate browser tests", "/e2e-tests", "test the login/checkout flow end to end". Playwright-first; drives the running app to capture real selectors and verifies each spec to green. Do NOT use for unit/integration tests, API-only tests, CLI tests, or non-Playwright e2e frameworks already present (it will stop).

Use when the user wants to create or update a pull request or merge request, open a PR/MR, push changes for review, update a PR description, or mark a draft as ready. Triggers on: "create pr", "open pull request", "make a pr", "submit mr", "merge request", "push for review", "ready for review", "/pr", "open mr", "ship it", "send for review", "update the pr", "update the description", "mark as ready".

Use after a pull request or merge request exists to drive it to a mergeable, green state — poll CI/GitHub Actions until it passes, detect and resolve merge conflicts against the base branch, read failing-check logs, apply fixes, push, and re-poll in a bounded loop. Triggers on: "make CI pass", "watch the PR", "babysit the PR", "get this PR green", "fix the merge conflict", "is my PR mergeable", "wait for checks", "/pr-guard", "保证 CI 通过", "看着 PR 直到合并", "解决冲突", "盯着 actions". Hand-off target after devpilot:pr-creator.

Use when writing, reviewing, or refactoring code and judging quality at the level of naming, function size, comments, error handling, class design, test quality, or code smells. Language-agnostic; defer to language-specific style skills (e.g. devpilot:google-go-style) when they conflict.

Review Atlassian Confluence pages and leave comments (both inline and page-level). Use this skill when the user asks to review, give feedback on, or comment on a Confluence page. Triggers on Confluence page URLs, "review this confluence page", "comment on the doc", "give feedback on the wiki page", or any mention of reviewing Confluence content.

SEO-optimized blog and content writing skill. Use this skill whenever the user wants to write a blog post, create content for their website, improve SEO rankings, do keyword research, or plan content strategy. Triggers on any mention of blog writing, SEO content, keyword research, content marketing, "写博客", "写文章", "内容创作", "SEO优化", or when the user wants to create any form of long-form content for a website or product. Even if the user just says "write something about X for our site", use this skill.

ALWAYS use when working in a Go project — writing new Go code, modifying .go files, reviewing Go PRs, or discussing Go design decisions. Triggers on any .go file interaction, Go package design, Go naming questions, Go error handling patterns, Go test writing, or Go code review. Even if the user doesn't mention "style" or "conventions", if you're touching Go code, this skill applies.

Use when setting up a repository for autonomous coding agents, adding guardrails, context files, or automation so agents ship reliably without constant review. Triggers on "make this repo agent-friendly", "agents keep drifting", "set up AGENTS.md / skills / sub-agents", "harness engineering", architectural drift with agent-authored code, or retrofitting guardrails after output quality decayed.

Turn a single article, document, or web page into a standalone HTML learning artifact: either a bilingual digest or a chaptered Chinese study guide with source summaries. MUST use this skill — not raw summarization — whenever the user asks to summarize, digest, get key points from, extract takeaways from, or turn a URL, PDF, .docx, .md, .txt, paper, report, or blog post into notes or study material. Trigger on: summarize this, key points, takeaways, digest, highlights, TL;DR, what does it say, overview, 学习资料, 学习笔记, 复习资料, 总结, 摘要, 要点, 重点, 提取, 整理, 讲了什么. NOT for: writing new content, translating, comparing two documents, building apps, multi-source news, code review, or data/CSV analysis.