Docs & Writing

baijunjie Bundle

创建 bug 工单。把缺陷整理成 docs/bugs/ 下的规范工单：现象、复现步骤、预期与实际、影响范围、验收判据；只写查证过的事实，不写修复方案。工单是一次性交接文档，修完即删、不维护。用于「记一个 bug」「提个工单」「把这个问题记下来」等场景。

taichuy Bundle

Use when a concrete engineering problem, bug, integration failure, dependency issue, unclear API usage, implementation blocker, or tool/capability need may already have a proven solution in GitHub open-source projects, issues, pull requests, discussions, code, examples, or release notes. Use it to find suitable repositories, report project basics including Stars when a repo-level solution applies, and adapt the existing solution with minimal local changes.

bankrbot Bundle

Bazaar (bazaar.playhunch.xyz): prediction markets anyone opens by tagging the bot, settled by the person who opened them, paid in USDC on Base. Trigger to make a market from a phrase or from the post being replied to ("market this", "make a market: will X happen by Friday?") and confirm its preview; to bet, quote or get odds on a Bazaar market (a bazaar.playhunch.xyz link, a Bazaar market id, the word "bazaar", or a reply in a Bazaar market's thread); to resolve or void a market you created, including "resolve YES" in the market's own thread; for standing bets ("bet $2 YES on every new bazaar market from @alice"), following or reporting on bazaar, win receipts and Bazaar event webhooks; and for my markets, markets to resolve, my Bazaar bets, results, a creator's record ("is @user trustworthy on bazaar?"), trending, closing-soon or resolving-soon markets, markets about a topic, leaderboards, share links, earnings and "bazaar help". Do NOT trigger for a bet with no Bazaar link, id, thread or the word bazaar (Po

parcha-ai Bundle

Self-QA a repo's running application end-to-end — discover how it runs, build a feature×modality test plan, execute it against a live instance, and produce a witnessed pass/fail report. Use when the user says "autoqa", "QA this repo/branch", "verify every feature works", "release readiness check", "test this like a QA engineer would", or another skill needs an automated QA pass before sign-off.

parcha-ai Bundle

Drive every reviewer thread on a GitHub pull request to zero unresolved in bounded iterations. Covers bot reviewers such as Greptile and Devin and human reviewers. Fetches every inline comment, review, and issue comment, fixes what is actionable, replies, resolves bot threads through GraphQL, re-requests review once per push, and ends with a fixed-format report. Use when the user says "review loop", "address the review comments", "get this PR to zero unresolved", "greploop", or "make Greptile happy".

theexperiencecompany Bundle

Generate a polished, printable PDF — reports, letters, invoices, resumes, one-pagers. Use when the user wants a PDF document. Typst is the primary engine; LaTeX (tectonic) is the fallback for niche packages or specific academic/journal templates.

theexperiencecompany Bundle

Generate an editable Microsoft Word (.docx) document — reports, letters, memos, structured docs. Use when the user wants a Word file. Built with docx-js (Node) for high fidelity.

theexperiencecompany Bundle

Generate a PowerPoint (.pptx) slide deck — pitch decks, reviews, summaries. Use when the user wants slides. Built with pptxgenjs (Node) for native, editable slides and charts.

getlago Skill

Numbered pagination rules for every list and table in lago-front: PaginatedContent, Pagination, usePageSearchParam, the mandatory createSinglePageFieldPolicy cache registration, and the sticky / insetPager / pageSize / page-reset choices. TRIGGER — read BEFORE writing the code whenever the task adds or changes a list, table or paginated query; whenever the diff mentions PaginatedContent, Pagination, usePageSearchParam, DEFAULT_PAGE_SIZE, PAGE_SIZE_OPTIONS, loadingRowCount, queryFieldPolicies, createSinglePageFieldPolicy, createPaginatedFieldPolicy or src/core/apolloClient/cache.ts; whenever a GraphQL field returns { collection, metadata } or takes $page / $limit; and whenever the report is that page 2 is empty, the pager is missing, the X-Y of N label disagrees with the rows, or a previously-viewed page flashes when re-entering a tab.

theexperiencecompany Skill

Read, search, and summarize Gmail — precise queries, large-inbox fan-out reads, synthesized findings, and the opinionated inbox triage report

theexperiencecompany Skill

Gather comprehensive Linear context — my tasks, sprint progress, blockers, team workload, prioritized status report

theexperiencecompany Skill

Manage Notion page content — insert, append, update blocks, delete blocks, override/replace content, and create new linked pages. Supports full markdown including tables.

theexperiencecompany Skill

Create Google Docs intelligently - choose right format, structure professionally, use markdown-first approach, handle templates and sharing.

babamba2 Bundle

ABAP code analysis — delegate source reads + AST/semantic/where-used analysis + rule-based review to sap-code-reviewer, then render a canned report or a richer briefing on the main thread

jesse-merhi Skill

Wait for a command, CI run, subagent, or timed delay by holding one long call instead of polling; report only meaningful state changes.

tifandotme Skill

Log repeated or systemic workflow friction to FRICTION.md at the workspace root. Use only when explicitly invoked to capture avoidable backtracking, repeated manual workarounds, tool failures, or documentation gaps that should become automation, docs, or workflow fixes.

tifandotme Skill

Reconstructs what the user did from their merged and open GitHub PRs and their Slack messages, then writes it as product-focused standup bullets. Use when the user asks to remember what they did yesterday, on a given day, or last week, or asks for help preparing a daily standup report.

thecolliery Bundle

Code-health scan — dead code, bug-prone logic, resource leaks, concurrency bugs, silent failures, input-boundary issues, doc rot. Triggers on: "/rot-canary", "rot-canary", "code-health" (legacy aliases: "/rotcanary", "rotcanary"). Auto-runs at session end on touched files (QUICK, report only) via platform hooks — auto-wired by the Claude Code plugin, manual elsewhere. Run manually for fix mode. Reports; fixes on request via choice-gated menu.

thecolliery Bundle

Code-health scan — dead code, bug-prone logic, resource leaks, concurrency bugs, silent failures, input-boundary issues, doc rot. Triggers on: "/rot-canary", "rot-canary", "code-health" (legacy aliases: "/rotcanary", "rotcanary"). Auto-runs at session end on touched files (QUICK, report only) via platform hooks — auto-wired by the Claude Code plugin, manual elsewhere. Run manually for fix mode. Reports; fixes on request via choice-gated menu.

lyravoid Skill

Extending or integrating Shirone's optional desktop context menu, including action registration, M3E keyboard behavior, shared clipboard actions, Swup lifecycle, and coordination with Markdown-rendered features such as code trees.

64x-lunicorn Skill

Records a project term in the CONTEXT.md at the project root as one line with its meaning, adding words to avoid only when another word for it actually came up, after Daniel confirms the exact line. Use when a word with one fixed meaning in this project comes up or settles that CONTEXT.md does not define yet, such as during an interview, a triage or an architecture review, when Daniel answers a question about a term's meaning or its line, or when a skill hands over terms to record, such as a Spec's terms.

lyravoid Skill

Authoring content with Shirone's custom Markdown syntaxes - admonitions, code trees, tabs, steps, field parameter cards, marker highlights, math, mermaid, image grids and sizing, abbreviations, annotations, spoilers, includes, and GitHub cards. Use when writing or editing Markdown/MDX content and choosing the right syntax.

yicheng47 Skill

Report, list, or manage bug reports as GitHub issues

64x-lunicorn Bundle

Writes a project's README.md in the house skeleton with centered header, banner, pitch, How it works, Quickstart, Documentation, Contributing and License sections, keeps the project's own sections on re-runs and reports drift. Use when a project gets its first README, when an existing README is brought to the house style, or when the README drifted after the license, the docs or the CI command changed.

64x-lunicorn Bundle

Reports a bug or a request about the 64x-lunicorn plugin to the plugin project on GitHub from inside any session, through a short interview and a draft that is filed only after the reporter confirms it.

sdvsignal Skill

Pre-commit gate. Run tests, lint and type check; report PASS/FAIL per step and anything that could not run. Use before any commit or PR.

sdvsignal Skill

Pre-commit gate. Run tests, lint and type check; report PASS/FAIL per step and anything that could not run. Use before any commit or PR.

btspoony Bundle

Morning Star plan harness artifacts — `{PLAN_DIR}` main plans and durable review summaries, `{SDD_DIR}/review/` ephemeral QC/QA bundles, `{KNOWLEDGE_DIR}` / `{ITERATION_DIR}` indexes, plus `{HARNESS_DIR}/status.json` (v2 root register) / `{WORKFLOW_DIR}/<id>/snapshot.json` (plan rows + leases + plan-scoped `coordination`/session/handoff/revision semantics) and `{PROJECT_DIR}/<id>/residuals.json` (residual register; severity SSOT, open/close lifecycle). Read when writing plans or QC/QA review bundles, maintaining knowledge/iteration indexes, reading or writing status/snapshot/register, or mapping QC severity to JSON. Required for `@project-manager` on status, residuals, and InReview/QC waves; `@qc-specialist*` before writing review bundle reports; `@qa-engineer` before closing R# when `QA gate: mandatory`. Verdict rules: leaf → `mstar-roles/references/qc-specialist/report-template.md`; PM → `mstar-review-qc`.

wkentaro Bundle

Simplify changed code without changing intended behavior. Use for /simplify, cleanup focused on reuse, unnecessary complexity, efficiency, or abstraction altitude, and report-only simplify reviews inside review-fix.

microsoft Skill

Use a shadow knowledge base to understand any codebase. The .shadow/ directory mirrors the source tree with markdown files containing behavioral insights — known bugs, edge cases, implicit contracts, and user preferences. Always check the shadow before editing, debugging, or investigating code. When the user shares important context, write it to the shadow immediately. Invoke shadow-frog-init to create it, shadow-frog-update to refresh it, shadow-frog-dream for autonomous exploration, shadow-frog-meditate for shadow hygiene, or shadow-frog-viewer to browse it.

microsoft Bundle

Initialize a shadow knowledge base for any codebase. Creates a .shadow/ directory that mirrors the source tree with markdown files for AI-discovered insights. Run this once per repo before using other shadow-frog skills. Refuses to overwrite an existing .shadow/ unless --reset is passed.

rojim666 Bundle

Create, edit, redline, and comment on `.docx`, Word, and Google Docs-targeted document artifacts inside the container, with a strict render-and-verify workflow. Use `render_docx.py` to generate page PNGs (and optional PDF) for visual QA, then iterate until layout is flawless before delivering the final document.

rojim666 Skill

将生成内容发布为在线链接，或取消发布已上线的应用。适合网站、小游戏等交互式内容，支持任意可作为单端口 HTTP 服务运行的项目（静态站点 / PDF / Node.js / Python / Go）。当用户想把本地项目部署、发布、上线、生成分享链接、在云端预览或下线分享链接时使用。

nudgebee Skill

Investigate a pull request end-to-end — predict how it could be wrong, run it for real, falsify those predictions with evidence, and report by severity

rojim666 Bundle

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

rojim666 Bundle

为专业幻灯片和可复用 PPT 模板提供视觉设计指导。适用于创建或优化 PPT/PPTX、选择审美方向、从参考图提炼视觉系统，以及改善层级、信息密度、字体、间距、构图与一致性；覆盖咨询研报、正式工作汇报、中国社区党建活动、高饱和艺术市集、编辑画册和历史教学等风格。