Docs & Writing

cuga-project Bundle

Generate human-readable API documentation from an OpenAPI / Swagger spec on disk. Lists endpoints, expands schema $refs, and writes per-endpoint sections with realistic curl examples and response shapes. Use when the user asks to "document this API", "generate docs for <spec.json|spec.yaml>", or paste an OpenAPI spec path.

cuga-project Bundle

Generate Mermaid.js architecture diagrams from natural-language system descriptions. Returns a fenced ```mermaid block ready for any markdown renderer, plus a brief components explanation. Use when the user asks for a diagram, flowchart, sequence diagram, ER diagram, or wants to "draw" a system.

cuga-project Bundle

Run a one-shot web research pass — multiple targeted queries, synthesise findings, cite sources. Use when the user asks "research X", "what's the current state of Y", or "find me info on Z" and wants a structured report (not just a single page summary).

cxrxhz Skill

Convert a paper, abstract, or research project into a conference-talk slide outline, speaker notes, and talk script without requiring Beamer/PPT compilation.

dafang Skill

Issue 流程路由。触发：修 bug/有问题/修复 XX；按状态进入 report/analyze/fix。

dafang Skill

Issue 报告起草。触发：提 issue/记录 bug/发现问题；只问现象，不猜根因。

dafang Skill

Issue 根因分析。触发：已有 report 后找根因、评估风险、给修复方案；不改代码。

erich3000 Bundle

This skill should be used when the user asks to "import Trello boards", "convert Trello JSON to Markdown", "generate Obsidian notes from Trello", or has placed Trello JSON exports at the repository root. Converts Trello board JSON exports into browsable Obsidian Markdown notes organized by board, list, and card.

erich3000 Bundle

Use this skill when the user asks to "neutralize a pptx", "neutralize a presentation", "standardize a PowerPoint", "normalize slide styling", or wants to apply uniform background color, fonts, text color, and remove text shadows from a .pptx file.

erich3000 Skill

This skill should be used when the user asks to "proofread markdown", "check for typos", "fix grammar", "review markdown file", or requests proofreading markdown content for quality assurance.

erich3000 Bundle

This skill should be used when the user asks to "set thumbnails for Trello cards", "add thumbnail frontmatter", "populate thumbnail field", or wants to add a `thumbnail` frontmatter field from the first image found in imported Trello card Markdown files.

erich3000 Bundle

This skill should be used when the user asks to "download Trello images", "localize Trello media", "download attachments from Trello cards", or wants to store Trello-hosted images locally in the vault. Downloads Trello-hosted images referenced in imported Markdown files and rewrites links to local paths.

moda-design Bundle

LinkedIn creative: posts, document carousels (exported as ONE multi-page PDF), banners, company-page art.

narenaryan Skill

Use when designing or reviewing tests, debugging plans, regression suites, process metrics, documentation templates, predictive models, or root-cause analyses to remove redundancy and keep only the smallest evidence set that still supports the decision

rami-maalouf Bundle

Generate and validate frontmatter metadata for markdown transcriptions and voice notes. Use when processing raw transcriptions, enriching Letterly notes, or preparing notes before moving them to final outputs.

rami-maalouf Bundle

Generate evidence-backed personal principles from markdown notes, reflections, and transcripts. Use when extracting life principles, decision rules, or lessons from journal entries and reflections.

rami-maalouf Bundle

Condense a folder of existing communication analysis artifacts into one folder-level markdown and JSON summary. Use this when the user already has per-file analysis reports and wants recurring weaknesses, vocabulary patterns, strongest counterexamples, or weekly priorities surfaced across a folder.

rami-maalouf Bundle

Analyze a markdown transcript into a communication coaching report covering speech flaws, vocabulary, clarity, persuasion, and habits. Use when the user wants feedback on a spoken note or transcript.

rami-maalouf Bundle

Route a markdown file or a folder through the communication skill suite automatically. Use this whenever the user points at a path and wants the system to figure out whether to run single-file communication analysis or folder-level communication summarization without making the user choose the flow manually.

rocm Skill

Use when creating or editing a SKILL.md file under .claude/skills/. Defines the TDD-for-documentation discipline, structure, and CSO rules that every amd-smi skill must follow.

rcarmo Skill

Write and review concise technical documentation using a plain-English voice guide and anti-trope filter. Use for READMEs, design notes, runbooks, API documentation, release notes, and pull-request text.

rcarmo Bundle

Fetch a user's recent tweets (tweets, replies, retweets) using Playwright + Nitter fallbacks and produce compact JSON/Markdown summaries.

rcarmo Bundle

Situate yourself by generating a 1-page situation report and maintaining Obsidian-style daily summary notes.

saturate Skill

Records architecture decisions to memory provider when significant technical choices are made. Lightweight format capturing what was decided, why, alternatives considered, and tradeoffs. Use when recording a decision, documenting architecture, ADR, architecture decision record, why did we choose, technical decision, or when a significant choice is made about dependencies, patterns, or infrastructure.

gsd-build Skill

Post-mortem a failed GSD auto-mode run. Traces from symptom to root cause using `.gsd/activity/*.jsonl`, `.gsd/journal/YYYY-MM-DD.jsonl`, `.gsd/metrics.json`, and `.gsd/auto.lock`. Produces a filing-ready bug report with file:line references and a concrete fix suggestion. Use when asked to "forensics", "post-mortem", "why did auto-mode fail", "trace the stuck loop", "debug the crash", after `/gsd forensics` is invoked, or when a session ended in an unexpected terminal state. Reads existing artifacts — does NOT re-run anything.

shimo4228 Bundle

daily-research のリサーチレポートから X (Twitter) 投稿用の日本語長文下書きをオンデマンド生成する対話 skill。Use when the user says 「X に投稿したい」「X 用の下書き作って」「これポストしたい」「ツイートにして」, invokes /x-draft, or mentions turning a daily-research report into a social media post — even if they just say 「今朝の akc のやつ X に流したい」 like shorthand. pull 型: 通知もノルマもなく、ユーザーがレポートを読んで投稿したいと思ったときだけ呼ぶ。軽量事故ゲート (一次ソース再確認 + 3 日陳腐化チェック) と脱 AI-tell 改稿を通した、コピペ 1 回で投稿できる長文 1 ポストを出力する。NOT for: 記事・エッセイ執筆（→ writing-ecosystem）、公開スレッドへの返信（→ public-comment）、タイトル・一行コピーだけの生成（→ headline-craft）、X への自動投稿（本 skill は下書きまで — 投稿は人間が行う）。

aaddrick Skill

Use when categorizing vocabulary into psychological dimensions (cognitive processes, social drives, biological needs, emotional states), identifying dominant psycholinguistic registers in a text corpus, performing dictionary-based word categorization for style profiling, or needing to map linguistic dimension distributions to style replication priorities

aaddrick Skill

Use when extracting a stable writing fingerprint from a text corpus based on function word frequencies, sentence structure patterns, and punctuation habits, defining syntactic constraints that make an author's writing identifiable regardless of topic, or building a replicable style profile from distributional features rather than content words

aaddrick Skill

Use when analyzing how an author constructs arguments beyond the word level, examining argument ordering patterns, rhetorical devices like hedging and concessions, discourse marker usage, paragraph structure distributions, or needing to produce replicable structural constraints from a text corpus for voice replication or argumentation profiling

danielscholl Bundle

OSDU QA Testing - Environment management, API test execution, failure analysis, and report generation. Use when running OSDU API tests, analyzing failures, comparing environments, generating QA reports, or managing test environments. Not for: unit testing application code or build compilation (use build-runner instead).

danielscholl Skill

Execute dependency remediation from an analysis report with validation, risk-tiered commits, and code fixes. Applies updates incrementally with build verification after each change. Use when the user has a dependency analysis report and wants to apply the recommended updates, or says "remediate", "fix dependencies", "apply updates". Not for: scanning dependencies (use dependency-scan), or general code fixes unrelated to dependency versions.

danielscholl Bundle

Analyze project dependencies for available updates, overlay CVE data, and create an actionable risk-scored remediation report. Supports Maven projects with Python and Node.js planned. Use when the user asks to scan dependencies, check for vulnerabilities, generate a dependency report, or says "what needs updating". Not for: applying dependency updates (use remediate), or general project build issues (use build-runner).

intel Skill

Analyze UT (unit test) results for a torch-xpu-ops PR. Use when asked to check test results, analyze CI failures, or evaluate test coverage for a PR. Produces a structured report of new failures, failure relevance, and new test coverage.

intel Skill

Shallow, text-only triage of a GitHub issue on pytorch or torch-xpu-ops. Classifies the issue and returns a report (markdown table + JSON) for the caller to act on. Read-only; the skill itself does not comment on or label the issue.

larsboes Bundle

Shrinks the files that load into every session — the user and project CLAUDE.md, their @-imports, the memory index — by removing what is provably dead first and then merging, tightening or relocating the rest behind a human gate, without ever dropping a distinct directive. Use when an always-on context file has grown too big, when asked to trim, shrink or prune CLAUDE.md, AGENTS.md or a memory index, when a rule set has turned into a document, or when the session's instruction budget needs to come down. Do not use for editing ordinary documentation, for refactoring code, or for removing AI writing tells from prose.

larsboes Skill

Builds a job-tailored CV PDF from a single profile-tagged master CV file, via the local `cv` CLI — pick the closest profile tag (or ask), pick a language, run the build, hand back the PDF path. Use when the user wants a CV/resume for a specific job application, role type, or language. Do not use for writing or editing CV content itself (that's the master file, edited by hand) or for any content-generation/AI-tailoring flow — this skill only filters and renders what's already in the master file.