17,425 tagged Writing and docs, measured the same way as everything else here.
Browse within: agent 154LLM 152cli 86skills 85agentic-ai 84agents 81seo 63javascript 53ai-coding 48ai-skills 47bioinformatics 45openclaw 44data-analysis 43claude-code-plugin 42
Skill Claude CodeCodex
Create and edit Obsidian vault content — Obsidian Flavored Markdown (.md), Bases (.base), and JSON Canvas (.canvas). Use this skill when working with Obsidian files, wikilinks, callouts, frontmatter, tags, embeds, Base views, filters, formulas, Canvas mind maps, building a no-database knowledge base / RAG vault (raw →…
Skill Claude CodeCodex
A workflow for turning an interview audio transcript into a question-and-answer review document.
Skill Claude CodeCodex
Write technical documentation following the Diataxis framework by Daniele Procida. Use when writing, reviewing, or restructuring documentation to ensure correct separation of tutorials, how-to guides, reference, and explanation.
Skill Claude CodeCodex
A development guide for working with Chinese-language requests. It sets conventions for Chinese comments, documentation, error explanations, and English names for Chinese concepts.
wsjwu58-cmd/Skill-Agents-Standard
Skill Claude CodeCodex
Generate and optimize AGENTS.md project documentation for AI coding agents. Scans project structure, detects tech stacks, extracts build/test/lint commands, and produces ready-to-use AGENTS.md files. Also audits existing AGENTS.md for completeness, accuracy, and best practices. Supports multi-editor output including…
Skill Codex
An instruction-file writing skill for creating, reviewing, or reorganizing AGENTS.md and CLAUDE.md files. These files give coding agents project facts and working rules, such as how to run tests or follow conventions.
Skill Claude CodeCodex
Maintain, create, migrate, and trim AGENTS.md or legacy CLAUDE.md instruction files for coding agents. Use this whenever the user mentions AGENTS.md, CLAUDE.md, agent rules, repo instructions, memory files, project guidance, instruction drift, or wants to standardize agent docs into a short, reliable source of truth.
Skill Claude CodeCodex
Set up or extend a "Hub-and-Spoke" agent documentation system in a repository — AGENTS.md as a table of contents pointing to spoke files (docs, agent instructions, runbooks, anything). Use this skill whenever the user wants to create or update AGENTS.md, add or restructure agent rules, migrate inline rules out of…
jeromekneip/ai-team-starterkit
Skill Claude Code
Document a repeatable process as a new skill or policy. Use when the owner says "make this repeatable", "document this process", "we should have a procedure for this", or when the same multi-step task has been done twice and will recur.
Skill Claude Code needs its repo
This skill migrates existing Markdown documentation into a modular Single Source of Truth (SSOT) structure managed by docs-ssot, then builds and validates the output.
Skill Codex
Um guia para explicar alterações de código, diferenças entre versões, ramificações e solicitações de mudança, desde o contexto até o funcionamento da implementação. Pode transformar essa explicação em material de estudo em HTML ou no Notion.
Skill Claude CodeCodex
A skill that saves and uploads Markdown notes to HackMD, an online service for writing and sharing Markdown documents.
newtontech/PKU_PhD_Latex_Templete
Skill Claude Code
Run a 5-perspective independent review of the manuscript covering editorial fit, methodology, domain expertise, cross-disciplinary impact, and adversarial argument testing. Inspired by academic-research-skills multi-reviewer approach. Use for pre-submission quality check or simulating peer review.
Skill Claude CodeCodex
Create and update a folder/file knowledge base using agentic discovery. Covers KB bootstrap, single entry creation, and entry updates. Use this when asked to document a system, subsystem, concept, or domain — or when existing KB entries need refreshing.
Skill Claude CodeCodex
A writing tool for preparing short weekly reports about a product or project launch.
Skill Claude CodeCodex
A delivery-summary tool for completed user stories, smaller tasks, or bug fixes. It produces the summary in the conversation and as Markdown and HTML files.
Skill Claude CodeCodex
Guidance for documenting web APIs with OpenAPI, a standard format for describing endpoints, inputs, outputs, examples, and errors.
longranger2/project-doc-bootstrap
Skill Claude CodeCodex
Bootstrap a reusable repository documentation hierarchy for AI agents. Use when starting a new project, initializing repo docs, setting up CLAUDE.md and AGENTS.md, defining L1/L2/L3 documentation layers, creating AGENTS.md symlinks, or designing a fractal documentation system that helps AI quickly understand and…
hannsxpeter/authenticity-check
Skill Claude Code
Score how authentically text reads as a real human author's work, flag spans that read as AI-generated, AI-templated, or generically derivative, and run a separate read-only scan for suspicious Unicode provenance carriers. Return an authenticity band, a 0-100 score, provenance signals, and span-level reasons. Use when…
Skill Claude CodeCodex
Writing rules for prose that does not read as AI-generated. Covers inflated importance, promotional wording, vague attribution, forced rules of three, em dash and bold abuse, chatbot fingerprints. Load before drafting or editing prose that lands in a deliverable (README, doc, report, ficha). Chat replies to the user…
Skill Claude Code
Explain and reply in clear, concrete English for a reader whose first language is not English - common words, one idea per sentence, real examples, each technical term defined once, no idioms and no hype. Keep the meaning exact; only the wording gets simpler.
Skill Claude Code
A skill that analyzes the current project's code and creates or updates a Korean-language .claude/codebase.md summary.
Applied-AI-Society/minimum-viable-jarvis
Skill Claude CodeCodex
Extract a single stuck thought, conviction, plan, sermon idea, principle, or insight from the owner's head into a clean artifact in the workspace. Use when the owner says "decongest", "I have something in my head", "I keep meaning to write about X", "help me get this out", "let me dump", "I'm clogged on Y", or…
Skill Claude CodeCodex
Audit, write, or revise .vale.ini, or work through vale findings on a repo. Use when adding Vale, troubleshooting silent passes or noisy findings, evolving config, or applying the suggestion → warning → error cleanup cascade after a vale run (interactive or pre-commit failure). Applies the two-hook pre-commit pattern…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: