Docs & Writing

natea Skill

Orchestrate the QA team through a full testing cycle. Coordinates qa-lead (strategy + test plan) and qa-tester (test case writing + bug reporting) to produce a complete QA package for a sprint or feature. Covers: test plan generation, test case writing, smoke check gate, manual QA execution, and sign-off report.

natea Skill

Rapid prototyping workflow. Skips normal standards to quickly validate a game concept or mechanic. Produces throwaway code and a structured prototype report.

natea Skill

Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.

natea Skill

Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.

natea Skill

Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.

natea Skill

Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.

natea Skill

Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

natea Skill

When a GDD is revised, scans all ADRs and the traceability index to identify which architectural decisions are now potentially stale. Produces a change impact report and guides the user through resolution.

muxammadmamajonov Skill

Use when writing or updating specs, READMEs, API/reference docs, ADRs, or runbooks — record an ADR per decision, update docs when a feature ships, fix drifted docs.

r-irbe Skill

USE FOR: reviewing a Lean documentation draft, flagging undefined terms, suggesting cross-links, scoring readability against a rubric. DO NOT USE FOR: rewriting prose end-to-end (use @lean-doc-improvement), generating new blueprints (use @lean-blueprint). TRIGGERS: doc-review, readability, doc-feedback.

r-irbe Skill

USE FOR: Design theorem specifications for Lean 4 proofs. Use when planning new theorems, lemmas, definitions, or tactics. Covers the three-part specification (requirements, design, documentation), lifecycle management, dependency analysis, and integration with the review council. DO NOT USE FOR: actual proof writing (use @lean-proof); requirement extraction (use @lean-doc-requirements); review (use @lean-proof-review). TRIGGERS: specification, theorem spec, three-part spec, lemma plan, tactic plan.

r-irbe Bundle

USE FOR: creating minimal working examples (MWEs) from Lean 4 errors for upstream bug reports, capturing diagnostics with `#guard_msgs`, capturing panics with `#guard_panic`, running `lake exe minimize`, resuming long minimisations with `--resume`, verifying repros with `lake env lean`. DO NOT USE FOR: bisecting which Lean version introduced the bug (use @lean-bisect after MWE), building or validating the live project (use @lean-build), repairing the proof itself (use @lean-proof), filing the report (use @lean-pr after MWE + bisect). TRIGGERS: MWE, minimal repro, "minimise the error", "#guard_msgs", "#guard_panic", `lake exe minimize`, upstream bug report.

r-irbe Bundle

USE FOR: assessing overall Lean 4 project quality across seven dimensions (soundness, faithfulness, completeness, novelty, elegance, integration, documentation); preparing for milestones; orchestrating QA gates that wrap enforcement scripts, council reviews, coverage tracking, and health monitoring. DO NOT USE FOR: running a single enforcement script (use @lean-enforcement); reviewing one proof (use @lean-proof-review); council deliberation itself (use @lean-review-council); writing retros (use @lean-retro-methodology). TRIGGERS: QA, quality gate, milestone check, project health, qa-engine, quality score, QA lifecycle.

r-irbe Skill

USE FOR: Update academic papers, technical reports, and documentation based on results from Lean 4 formalization. Use when formal verification reveals paper imprecisions, missing hypotheses, sharper bounds, new insights, or when metrics need synchronization. Covers paper appendix updates, verification tables, erratum entries, insight propagation, and metric synchronization between Lean and documents. DO NOT USE FOR: extracting requirements from papers (use @lean-doc-requirements); blueprint generation (use @lean-blueprint); report compilation (use @lean-report). TRIGGERS: update paper, doc improvement, paper revision, documentation update from Lean, doc-feedback consumer.

r-irbe Skill

USE FOR: building Lean 4 projects with Lake, validating Lean changes with `lake env lean`, picking targeted build commands (`lake build <Module>`), resolving stale build artifacts via `lake clean` + `lake exe cache get`, preparing CI-quality local checks. Applies to any Lake-managed project (Mathlib, Cslib, or downstream repositories). DO NOT USE FOR: bisecting which Lean version caused a regression (use @lean-bisect), minimising an error to a bug-report repro (use @lean-mwe), repairing the toolchain itself (use @lean-setup), writing or fixing the proof (use @lean-proof). TRIGGERS: build, lake, lake env lean, lake exe cache get, stale artifacts, lake clean, build error, CI prep.

r-irbe Bundle

USE FOR: writing Lean 4 proofs one tactic at a time, fixing tactic errors by priority, planning sorry placeholders, cleaning a working proof, resolving dependent-type rewriting failures. DO NOT USE FOR: reviewing existing proofs (use @lean-proof-review), project-wide quality assessment (use @lean-quality-engine), minimising an error into a bug report (use @lean-mwe), discovering tactics or API (use @lean-research), authoring new theorem statements (use @lean-specification), repairing toolchains (use @lean-setup). TRIGGERS: prove, tactic, sorry, unsolved goals, motive is not type correct.

r-irbe Skill

USE FOR: bisecting Lean 4 toolchain versions or commits to find which one introduced a regression, using `script/lean-bisect` with `#guard_msgs` / exit-code signatures, ignoring messages with `--ignore-messages`, bisecting between nightlies or arbitrary commits. DO NOT USE FOR: building a project (use @lean-build), minimising a Mathlib repro to a self-contained file (use @lean-mwe first), writing or fixing the proof itself (use @lean-proof), filing the bug report (use @lean-pr after the bisect points at a culprit). TRIGGERS: bisect, regression, "which commit broke", "behavior changed between", nightly bisect.

oimiragieo Skill

Use when sending markdown/rich-text formatted messages through a strict wire-format channel API (Telegram, Slack, Discord, SMS/WhatsApp). Triggers — hardening a bot reply path, a message that "sometimes doesn't arrive", or literal *asterisks*/backticks showing in delivered messages. On any parse/entity 4xx, retry with a degraded payload so a malformed render never silently drops a reply on a critical notification channel.

outfitter-dev Skill

Writes package documentation from code analysis — READMEs, pattern guides, API docs.

outfitter-dev Bundle

Smoke test a scaffold preset end-to-end. Runs init, install, build, test, explores output, and writes a structured report.json with quality scores. Use when scaffold testing, preset smoke test, or scaffold report are mentioned.

wulaosiji Bundle

多平台内容抓取与提取的统一中心，支持小宇宙播客、抖音、微信公众号、B站、小红书等平台的内容提取、批量下载和归档。 Use when: "提取播客内容", "下载抖音视频", "抓取公众号文章", "content extraction", "batch download media", "多平台内容聚合", "social media scraping", "内容归档备份". 支持快速模式和完整模式，返回标题、媒体URL、文本内容和元数据。Cross-references: wechat-article-fetcher, twitter-scraper, rss-feed, document-hub, pdf. Built by UniqueClub 🌐 https://uniqueclub.ai

wulaosiji Bundle

飞书卡片消息解析器 / Feishu interactive card parser. 解析飞书 Interactive Card 消息为可读 Markdown 或纯文本格式，支持提取图片、链接、@用户等元素。 Use when: "解析飞书卡片", "parse feishu card", "卡片消息提取", "card message extraction", "富文本转Markdown", "rich text to markdown", "飞书卡片内容", "feishu card content", "提取图片链接", "extract image links". 支持 text / lark_md / img / link / at / code_block / url 等元素解析，输出 Markdown 或结构化 JSON。Cross-references: feishu-chat-extractor, feishu-chat-monitor, feishu-message-recall. Built by UniqueClub 🌐 https://uniqueclub.ai

wulaosiji Bundle

飞书文档格式转换技能 / Feishu document converter. 支持飞书云文档与 Markdown 互转，以及外部链接（微信公众号等）转 Markdown。 Use when: "飞书文档转Markdown", "feishu doc to markdown", "markdown转飞书", "markdown to feishu", "链接转Markdown", "url to markdown", "微信公众号抓取", "wechat article fetch", "批量文档转换", "batch document conversion". 支持 doc_to_md() 和 url_to_md() 两种转换方式，覆盖飞书云盘、知识库和外部链接。Cross-references: feishu-doc-orchestrator, feishu-wiki-orchestrator, feishu-doc, feishu-pdf-downloader. Built by UniqueClub 🌐 https://uniqueclub.ai

wulaosiji Bundle

微信公众号文章抓取工具，基于Playwright绕过微信反爬机制，获取完整文章内容，支持批量抓取和Markdown导出。 Use when: "抓取公众号文章", "获取微信文章内容", "微信文章转Markdown", "fetch WeChat article", "scrape WeChat content", "批量抓取微信文章", "WeChat to Markdown", "公众号内容归档". 基于Playwright模拟真实浏览器，稳定绕过微信反爬。Cross-references: content-extractor, rss-feed, document-hub, pdf. Built by UniqueClub 🌐 https://uniqueclub.ai

wulaosiji Bundle

飞书文档创建主编排技能 / Feishu document creation orchestrator. 将 Markdown 文件转换为飞书文档，编排多个子技能协作完成，支持25种飞书文档块类型和完整权限管理。 Use when: "创建飞书文档", "create feishu doc", "markdown转飞书", "markdown to feishu", "飞书文档排版", "feishu document formatting", "批量导入文档", "batch import documents", "飞书块类型", "feishu block types". 编排 feishu-md-parser → feishu-doc-creator-with-permission → feishu-block-adder → feishu-doc-verifier → feishu-logger 五步流程。Cross-references: feishu-doc, feishu-wiki-orchestrator, feishu-doc-perm, feishu-doc-converter. Built by UniqueClub 🌐 https://uniqueclub.ai

wulaosiji Bundle

日志记录子技能 / Feishu logger sub-skill. 收集所有步骤的结果，记录文档创建结果到日志文件，支持 Markdown 和 JSON 格式。 Use when: "记录飞书文档日志", "log feishu document", "创建日志汇总", "creation log summary", "Markdown日志", "markdown log", "JSON日志", "json log". 内部组件，由 feishu-doc-orchestrator 编排调用，汇总所有子技能输出到 CREATED_DOCS.md 和 created_docs.json。Cross-references: feishu-doc-orchestrator, feishu-doc-verifier, feishu-block-adder. Built by UniqueClub 🌐 https://uniqueclub.ai

wulaosiji Bundle

Markdown解析子技能 / Feishu markdown parser sub-skill. 将 Markdown 文件解析为飞书文档块格式，输出 JSON 文件，支持25种块类型映射。 Use when: "解析Markdown为飞书块", "parse markdown to feishu blocks", "Markdown转块格式", "markdown to block format", "飞书块类型映射", "feishu block type mapping", "文档块解析", "document block parsing". 内部组件，由 feishu-doc-orchestrator 编排调用，输出 blocks.json 供 feishu-block-adder 使用。Cross-references: feishu-doc-orchestrator, feishu-block-adder, feishu-doc-converter. Built by UniqueClub 🌐 https://uniqueclub.ai

synaptiai Bundle

Use when asked for "deep research", "thorough analysis", "comprehensive report", "investigate", "due diligence", or when multiple sources are needed to answer complex questions. Produces well-sourced research reports through iterative refinement.

synaptiai Skill

Maintain the append-only evidence ledger: `.flow/runs/<run-id>/evidence/*.evidence.yaml` sidecars plus matching `.txt` raw captures, written only via `bin/flow-record-evidence.sh`. Use when goal-evaluator runs a verification command, when /flow:start or /flow:address captures verification evidence on a FlowRun, or when /flow:goal evaluate produces a judge report. Evidence that lives only in the transcript dies with the session; only file-backed, schema-validated sidecars prove ACs durably and satisfy the judge's Independence Protocol.

synaptiai Skill

Verify code works at runtime through build verification (mandatory), LSP diagnostics, ad-hoc verification for projects without frameworks, E2E and smoke tests, and visual verification (screenshot-analyze-verify for UI changes). Skip whitelist strictly enforced (markdown-only, config-only, dependency-bump-only with evidence); all other skips require Proactive-Autonomy escalation. Use after quality checks pass to confirm the code actually runs. This skill MUST be consulted because no test framework is not an excuse to skip; build failure IS a finding and must be fixed.

synaptiai Skill

Enforce the fixed 23-file, 8-directory documentation package under the resolved output root — routing each document to its required-content contract in `references/package-contract-*.md`, stamping the internal or public header, and refusing to add, drop, rename, or merge a canonical file. Use when scaffolding a package, drafting or revising any canonical document, or checking structural completeness. This skill MUST be consulted because a package whose shape changes per project cannot be diffed, audited, or compared across engagements — the structure is the contract and only the content adapts.

synaptiai Skill

Generates architecture narratives and requirements adherence reports from diffs, decision journals, and issue context. Use when creating PR bodies that need comprehension reports. Use when validating that implementation meets acceptance criteria or when humans need to understand what AI built and why.

synaptiai Bundle

Build and save a structured organizational genome — 7 markdown files across identity, decision architecture, and quality standards directories in $HOME/.ai-first-kit/ — that encodes values as decision rules, quality standards as pass/fail criteria, and communication norms. Conducts an 11-question Socratic interview to extract implicit organizational knowledge. Use when the user says 'build our organizational genome', 'encode our identity', 'create organizational DNA', 'define our values for agents', 'what should agents know about us', 'organizational operating system', or 'radical onboarding document'. Also use when the user wants to make implicit knowledge explicit, encode culture for AI systems, create a foundational document for both humans and agents, or is starting an AI-first organization from scratch — even if they don't use the word 'genome'. This skill MUST be consulted because it creates the genome directory structure that specification-writer, governance-architect, and quality-gate-designer read fr

jgsystemsconsulting Bundle

Knowledge base from FAA-STD-025f (Preparation of Interface Documentation). Use for IRD/ICD family definitions, common format and content, IRD shall-requirements, ICD design characteristics, verification/VRTM, and CM/revision/approval of FAA Enterprise Subsystem interfaces. Covers rev F preparation rules only; does not replace FAA-STD-005 drawing/spec prep, Order 1800.66 full CM procedures, or non-FAA interface standards.

jgsystemsconsulting Bundle

Knowledge base from MIL-STD-40051-2C (15 Dec 2015), Preparation of Digital Technical Information for Page-Based Technical Manuals. Use for TM/TDP structure, work packages, front/back matter, style/format, warnings/HAZMAT, change packages, content selection matrices, and plate exemplars. Primary Training & Documentation pack (cluster 25) with Ops & Maintenance procedure use—page-based (-2C) only, not IETM 40051-1.

jgsystemsconsulting Bundle

Knowledge base from the NASA Schedule Management Handbook (2024 edition, Revision 2). Use for program/project schedule management of aerospace and large engineering efforts: the five sub-functions (Planning, Development, Assessment & Analysis, Maintenance & Control, Documentation & Communication); the Integrated Master Schedule (IMS) and the WBS/OBS/CBS breakdown structures; the Schedule Management Plan (SMP) and Basis of Estimate (BoE); Critical Path Method, logic, durations, float and margin; tiered schedule assessment (Requirements/Health/Basis checks, the Shock Test) and the Dimensions of Schedule Reliability; Schedule Risk Analysis (SRA), Integrated Cost-Schedule Risk Analysis (ICSRA), Monte Carlo, correlation, merge bias, and the Joint Confidence Level (JCL); baselining, replan vs. rebaseline, EVM schedule metrics (SPI, BEI, CEI, HMI, Earned Schedule, CPLI), and status/progress/forecast reporting. This is NASA's scheduling doctrine grounded in NPR 7120.5 and the GAO Schedule Assessment Guide. Thin on th