Docs & Writing

mehdiforoozandeh Skill

Write the Requirements Document for a crux node — the design detail that does not fit, and should not fit, inside a 400-word question or hypothesis. An RD is one immutable design document per node, living in `rd/` beside the tree, linked from the node, outside the roll-up: the estimand and its bound, the probe ladder, the negative control, the known distortion that must travel with every result. You do not interview and you do not re-derive — you write up the design that has just been settled in conversation with the PI, and you apply the write-vs-skip filter that stops every node from growing one. A design change is never an amendment: it is a new RD that supersedes the old, and the chain is the reasoning history. Invoke explicitly — the PI decides when a design has settled.

meisijiya Bundle

简历优化与包装,酥神 + GodSU 融合方法论。含 10 条军规体检、四段式改写、防伪审计、一页 A4 PDF 渲染。当用户要优化/包装/重写/写简历、抱怨简历被筛、或说"酥神同款"时使用。

meridianlabs-ai Skill

Merge approved upstream inspect_ai PRs from the Atlas board's Merge stage, one at a time — resolve conflicts against main, guard CHANGELOG/submodule invariants, coordinate companion ts-mono PRs and submodule pointer bumps when the viewer schema changed, watch CI, merge, and clean up the board. Handles both promotions (our branches) and approved External contributor PRs (their fork branches; maintainerCanModify is the prereq — skip and report those without it). Items whose issue carries hold:release are skipped unless holds are explicitly included (the post-release sweep). Use when Ransom says he's ready to merge approved PRs / clear the Merge queue.

rodydavis Bundle

Auto-correct relative links, asset paths, and related links in markdown documents based on folder depth.

rodydavis Bundle

Process all markdown documentation files to generate AI summaries and embeddings (using Ollama), apply taxonomy tags, and compute KNN related links.

rodydavis Bundle

Ensure all markdown documents have their frontmatter titles injected as standard H1 headings at the start of the body.

romiluz13 Skill

Use DDD for coding tasks: discover the official documentation needed for the requested behavior, plan with cited snippets, keep one persistent task note, implement, and compare code against the sources. Also use when resuming work or debugging unexpected behavior that challenges an implementation assumption.

romiluz13 Skill

Produce a documentation-grounded plan with cited decisions and integration snippets, save its research, or continue an authorized implementation.

rondomondo Bundle

Generates Find4 game JSON from any text source — a URL, a local file, or piped stdin content. Find4 is a Connections-style word-grouping game (https://find4.org) where players find groups of 4 words that share a hidden theme. Use this skill whenever the user wants to: create a Find4 game, generate game content from a document or webpage, produce a game JSON file, analyse text into themed word groups, or populate the Find4 library. Also trigger when the user mentions "connections game", "word groups", "concept groups", or "game JSON", or uses vague phrasing like "make a game from this" or "turn this into something interactive" when a URL, file, or document is present.

scisharp Bundle

NumSharp's NumPy-vs-NumSharp performance harness — the op/dtype/N matrix (C# BenchmarkDotNet vs a warm NumPy process), unified Managed/OpenBLAS backend profiles, and five appended subsystems (nditer, layout, operand, cast, fusion), all in the NPY/NS convention. Use this whenever you add a benchmark for an np.* op, wire a C# benchmark to its NumPy twin, run the official suite or a subset, read/interpret the ratio matrix or history snapshots, add a whole subsystem, or debug a suspicious measurement (the Debug-taint 2x pitfall, the InProcessEmit toolchain). Trigger on: "benchmark", "add a benchmark", "how fast is np.add vs numpy", "run_benchmark.py", "BenchmarkDotNet", "NPY/NS ratio", "perf comparison", "benchmark np.add", "benchmark-report", "history snapshot", "why is my timing 2x slow". Reach for it before quoting any NumSharp-vs-NumPy speed number.

scottwater Bundle

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

sfrangulov Bundle

**Consulting Problem Solving Framework**: An interactive, user-led approach to solving complex business and organizational problems using structured consulting methodology. You act as a consulting associate; the user acts as the consulting partner who drives decisions. Walks through problem definition, MECE structuring, prioritization, work planning, analysis, synthesis, recommendations, and communication — with the user providing input, making choices, and reviewing deliverables at every step before moving forward. Produces deliverables at each stage — markdown working docs, spreadsheets for data analysis, and final slide content (.md) or approved content for a vertical document. This skill owns content and structure only — visual rendering, styling, and deck/document generation are handled by downstream builder skills. All final prose is polished using an integrated Strunk & White writing style guide. Use this skill whenever the user mentions: strategy consulting, problem solving framework, issue tree, MECE

chianglianglin Skill

Run a four-pass literary review of a chapter — produces a scored editorial report with specific improvement directives, and optionally applies rewrites and saves an improved version.

claude-world Skill

Fetch external documentation sites and convert to local markdown for context

cloudflare Skill

Style guidance for the written word. Use when asked to write code comments, commit messages, pull requests, READMEs, or documentation. Triggers might be phrases like "write a commit", "document this", or "add a README".

cloudflare Skill

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

cmg8431 Skill

Generate a weekly report of detected patterns and rule effectiveness. Use when user asks "dejavu report", "what did you learn this week", "dejavu weekly".

codelytv Bundle

Create new documentation based on the current conversation context.

corticalepilepsyladyofthehouse956 Skill

Use this skill when the user needs to pull structured data out of a document file — tables, form fields, line items, or plain text. Handles scanned and digital documents, and works even when the user does not say which format they have.

cosmtrek Skill

Conduct web-backed research with Exa search and write a Markdown report. Use when a task asks for current research, market/news analysis, or source-grounded synthesis.

arcanedge-ai Skill

Use for a complex Claude Code task with substantial fan-out, several genuine dependencies, broad repository scope, layered consolidation, separate implementation and verification paths, or an approval-gated irreversible action. Makes the work topology explicit in Markdown, runs only the parts whose inputs are ready, preserves completeness through consolidation, and reruns only what a failure actually invalidated. Skip it for small or genuinely linear work.

arunskiorg Bundle

Convert a text/markdown document into spoken-word MP3 audio, after rewriting the source into speech-friendly prose (making non-text elements readable aloud). Use when the user asks to convert a document to audio, to read something aloud, mentions TTS or "text to speech", or says to "speak" something. Do NOT auto-engage on bare "say" / "tell me" idioms — those usually want a visual reply; instead ask "btw, do you want mp3 output?" - in that case, only run this skill if they confirm.

avinava Bundle

Design honest, accessible charts of quantitative data as inline SVG — bar and column charts, line and time series, limit ledgers, distributions, scatter plots, and small multiples. Use when visualizing measured values, choosing a chart type, picking or fixing chart colors, building a categorical palette from design tokens, setting axes and scales, labelling series, or making an existing chart readable in grayscale and in print. Do not use for diagrams of structure or process such as architecture or flows (use diagram-design), for the surrounding report narrative and metric semantics (use analytical-document-design), or for interactive dashboards that require a client-side charting library.

codesigils Skill

Review Python code style with emphasis on configured tooling, import organization, naming clarity, public API documentation, formatting consistency, and string transformation patterns. Use when reviewing style/lint changes, pyproject lint configuration, docstrings, imports, naming, readability issues, or pluralization logic after correctness findings.

con-benksl Bundle

Read-only scanning of clients, authorized VPS hosts, proxy nodes, and observable paths. Use when the requested outcome is evidence, comparison, a baseline, or existing monitor data, and when netops-fix needs evidence for an unknown failing segment. Report confidence and blind spots rather than claiming a complete physical route. 典型中文请求：扫描本机和 VPS、比较两台电脑、保存正常基线、收集故障证据。

devotts Skill

Generic autonomous QA suite for any project — reads a test plan (markdown file or inline spec), runs all tests using Chrome CDP + iterate cycles, fixes bugs found, and produces a final QA report. Works with any web stack. Trigger with /full-qa [path-to-test-plan.md]. Use before releases, after significant changes, or whenever you want a full system health check.

eonraider Bundle

Export the current fixture data to a formatted report file.

fyzel Bundle

Keep a GitHub project's documentation in sync with the code after a change — propagate feature, CLI, config, exit-code, or install changes across the README, in-repo guide files (CLAUDE.md, CONTRIBUTING, docs/), and the GitHub wiki. Use this skill whenever the user says "sync the docs", "update the docs", "doc sync", "update README and wiki", "keep docs in sync", after resolving an issue or merging a feature, or when a hook/reminder flags that source changed and docs may be stale. Works for any GitHub repo. Requires `git`; the wiki step needs the repo's wiki enabled, and pushing needs `gh`/git push access.

fyzel Bundle

Compose original songs as copy-paste-ready prompts for the Suno AI music generator (v5.5), producing three blocks — lyrics with Suno meta tags, a style description, and suggested titles. Use this skill whenever the user asks to "create a song", "write a song", "create a Suno song", "write a Suno song", "create song lyrics", or "write lyrics", or anything close such as turning a poem or idea or story into a song, asking for a track for Suno, requesting a chorus or verse or hook, or asking for a song about some topic. Trigger it even when the user does not say the word "Suno", as long as they want original lyrics or a song.

gggodlin Skill

Invoke when writing or editing English markdown content that will be shown to the user - skill SKILL.md files, CLAUDE.md edits in shared repos, plan files, README, design docs, technical proposals, RFC drafts. Generates a Traditional Chinese review copy at ~/.claude/review-zh/ so the user can review the gist in their native language. Skip when source is already Traditional Chinese, is pure code, or is trivial (commit messages, PR titles, short config comments). Also invokable manually via /review-zh.

howie126313 Bundle

Convert external URLs into structured Markdown and save to the Obsidian vault. Use when the user provides an external URL (article, blog post, tweet thread, newsletter) and wants it saved as an Obsidian note. Triggers: "save this article", "archive this link to obsidian", "bookmark article", or when user pastes a URL and asks to save/summarize/archive it.

giuice Bundle

Route a piece of work through the full long-horizon loop — specify, plan, execute, replan, report — by deciding whether the work warrants the loop, detecting which stage it is already in, and handing off to the right skill. Use this skill whenever the user asks to take something from idea to done, to handle a goal end to end, to run the full workflow, to work on something properly with a plan and evidence, or to resume, continue, or check where a previous run of this workflow stopped.

giuice Bundle

Produce the smallest user-facing report that preserves every material fact about a task outcome, by classifying the terminal state, comparing it against the contract, filtering activity out, and checking that no material fact was lost to compression. Use this skill at a task boundary — when work is complete, partial, blocked, or failed — whenever the user asks what the outcome was or for a summary of what was accomplished, and whenever an execution run ends and its result must be communicated. Reports consequences and evidence, never the execution trajectory.

glassflow Skill

Use when a design convention has just been decided (a time grammar, a head style, a title size, a state word, a colour rule) — lands the code, the .impeccable.md sentence, the field-manual paragraph and, when the rule has a signature, the design-contract lint, in one PR.

gogoingai Bundle

基于证据撰写中文内容的完整流程，涵盖调研、规划、提纲、逐节写作、审查、配图、翻译和发布 准备，适用于文章、报告、教程、项目介绍、解读和说明材料。当用户要求“写文章”“写报告” “写项目介绍”“源码解析”或“帮我写篇内容”，或使用 "write an article", "write a report", "analyze source code", "deep explanation" 等英文表达时使用。

haiyuan-ai Bundle

Convert Mermaid code blocks in Markdown to styled PNG or SVG images. Use for Mermaid export, image replacement, or visual polish. Supports `dark-tech`, `fresh-business`, `hand-drawn`, and `gradient-modern`.