Writing and docs

23,578 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

onboarding-email-seq

769

bluefox3186-f7i30/onboarding-email-seq

Skill Claude CodeCodex

A guide for writing a three-to-five-email activation sequence for developer tools, meaning emails that help new users reach their first useful result.

not rated 43 +10 1mo ago A 103 tokens original MIT

prompt-polish

770

mfarzanansari/prompt-polish

Skill Claude CodeCodex

Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for…

not rated 42 1mo ago A 146 tokens original MIT

algolia

772

SumoLogic/sumologic-documentation

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "algolia", hosted remotely at mcp.algolia.com, as configured in SumoLogic/sumologic-documentation.

not rated 42 today A tokens not measured original MIT

wiki

773

bearlike/Assistant

Plugin Claude Code

Bundles 8 agents · 309 tokens together

AI-generated documentation backend for code repositories.

not rated 42 3d ago A tokens not measured original MIT

doc-cleanup

774

aka-luan/doc-cleanup

Skill Claude CodeCodex

Audit and clean Markdown documentation for context rot. Use when docs may contain completed-work logs, executed plans, stale claims, contradictions, dead paths, or drifted authorities, especially in agent-required reading.

not rated 42 2mo ago A 44 tokens original MIT

requirements_spec

775

chaussky/ainalyst

Skill Claude CodeCodex

BABOK 7.1 skill — Specify and Model Requirements. Use this skill when the BA translates elicitation results into formal specifications: user stories, use cases, business rules, data definitions, process models (BPMN). Triggers: "requirements specification", "user story", "use case", "business rules", "specify…

not rated 42 +1 12d ago A 90 tokens AGPL-3.0

follow-up

776

humanizerai/agent-skills

Skill Claude Code

Write follow-up emails that re-engage without being annoying. Uses proven psychology for follow-up sequences. 42% of replies come from follow-ups.

not rated 42 +1 7mo ago A Socket: passSnyk: pass 33 tokens original MIT

docflow

777

MedAdemBHA/docflow

Plugin Claude Code

Bundles 9 skills, 3 commands · 492 tokens together

Adoption-aware documentation memory for AI coding agents. Scaffolds or adopts living docs, validates native and established structures with appropriate severity, upgrades managed helpers, and loads bounded recent context.

not rated 42 +1 28d ago A tokens not measured original MIT

contextlint-init

778

nozomi-koborinai/contextlint

Skill Claude CodeCodex

Bootstrap contextlint into a repository. Use this skill whenever the user wants to set up, install, initialize, or configure contextlint — even if they only say "lint setup", "doc integrity check", or "set up Markdown linting" without naming contextlint by name. Detects the package manager (bun/npm/pnpm/yarn), scans…

not rated 42 +1 1mo ago A SkillSpector: warn 146 tokens original Apache-2.0

ai-news-briefing

780

hoangsonww/AI-News-Briefing

Command Claude Code

Search for today's latest AI news and create/update a comprehensive briefing in Notion, with optional Obsidian vault publishing for graph visualization.

not rated 42 +1 4d ago A 26 tokens original MIT

ergo-backlog-planning

781

sandover/ergo

Skill Claude CodeCodex

Shape and execute multi-step work with the Ergo CLI, a repository-local backlog management tool. Use to plan software development, documentation, or general knowledge work as a series or graph of well-defined tasks. Use to define dependencies within that task backlog. Use to group tasks into epics when needed. Skip…

not rated 42 2d ago A SkillSpector: warn 73 tokens original MIT

weisi-gu/xiaoyuzhou-podcast-notes

Skill Claude CodeCodex

A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.

not rated 42 +3 2mo ago A 220 tokens original MIT

oh-my-resume

783

open-agent-power/oh-my-resume

Skill Claude CodeCodex

Use when creating, editing, checking, theming, or exporting resumes from Markdown with Oh My Resume. The skill includes a bundled CLI and templates, so users can ask for a resume PDF without installing the npm package first.

not rated 42 +4 changed 7d ago A 50 tokens original MIT

paper-writing

784

swarm-ai-research/swarm

Skill Claude CodeCodex

Scaffold research papers from SWARM run data with auto-populated tables.

not rated 42 +1 yesterday A SkillSpector: pass 17 tokens original MIT

sales-council

785

antonioc-cl/sales-council

Skill Claude CodeCodex

Expert sales council with 6 advisors (Cialdini, Hormozi, Rackham, Voss, Klaff, Schwartz) for pricing, persuasion, negotiation, copywriting, and pitch strategies.

not rated 41 7mo ago A 47 tokens original MIT

spec-to-readable-html

786

KeMezz/spec-to-readable-html

Skill Claude Code

Transform Markdown or text specifications into human-readable HTML documents with summaries, reordered structure, visual explanations, diagrams, charts, and traceability to the source. Use when asked to convert a spec, requirements document, API spec, product spec, design doc, or technical document into readable HTML…

not rated 41 3mo ago A 91 tokens original MIT

look-tongji-notes

787

WALKERKILLER/Look-Tongji-Notes

Plugin Claude Code

Bundles 11 skills · 613 tokens together

9 short commands (/setup, /list, /trans, /note, /wiki, /add, /page, /cheatsheet, /ralphtrans) for Tongji Look lecture transcription, supplementary material ingestion, course wiki generation, and GitHub Pages deployment.

not rated 41 3mo ago A tokens not measured original MIT

explain-report

788

minghinmatthewlam/agent-guards

Skill Codex

Create a self-contained HTML explanation when the user requests one or when important, durable project knowledge is materially easier to understand visually than in concise chat. Use for significant architecture, research, decisions, incidents, audits, or changes that the user may revisit. Do not use for routine…

not rated 41 +2 changed 8d ago A SkillSpector: warn 69 tokens original MIT

prompt-pack-support

789

fastlion4376-yrjda/prompt-pack-support

Skill Claude CodeCodex

A method for creating reusable customer-support prompts for people or chatbots. The pack can include tone rules, reply templates, escalation paths, refusals, privacy guidance, and quality checks.

not rated 41 +9 1mo ago A 71 tokens original MIT

NickCrew/Claude-Cortex

Skill Claude CodeCodex

User-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the…

not rated 41 +4 2mo ago A 180 tokens original MIT

event-catalog/agents

Skill Claude CodeCodex

Generates EventCatalog documentation files (services, agents, events, commands, queries, domains, flows, channels, containers, ADRs, data products, entities, diagrams) with correct frontmatter, folder structure, and best practices. Use when user asks to "document a service", "document an agent", "document an AI…

not rated 40 +1 2mo ago A 127 tokens

documenting-meetings

792

umairalipathan1980/Claude-Skill-for-Multimodal-Report-Generation

Skill Claude CodeCodex

Converts scattered meeting data (recordings, handwritten notes, diagrams, digital notes, supplementary documents) into a structured MS Word deliverable with summary, decisions, action items, open questions, and follow-up message. Use when the user mentions meeting notes, meeting summary, meeting minutes, action items…

not rated 40 7mo ago A 78 tokens

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: