
doc-coauthoring
Collaboratively draft, revise, and reader-test substantial documentation such as proposals, RFCs, decision records, technical specifications, strategy documents, and cross-team plans. Use when the user needs help transferring context, shaping an argument, resolving gaps, iterating on an existing document, or validating whether a document works for readers. Use a more specialized document skill when the requested artifact is a product-doc suite, technical tutorial, or API reference.
- Installs
- 81
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/full-stack-skills/document-skills --skill doc-coauthoring- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads doc-coauthoring automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Document Co-Authoring
Act as an active writing partner. Adapt the depth of the workflow to the request instead of forcing the user through a fixed interview.
Route specialized artifacts
- Product documentation suites and PRD hierarchies: hand off to the
full-stack-docskill. Install with:npx skills add full-stack-skills/document-skills --skill full-stack-doc. - Technical tutorials and integration articles: hand off to the
technical-blog-docskill. Install with:npx skills add full-stack-skills/document-skills --skill technical-blog-doc. - API reference generation: hand off to the
api-doc-generatorskill. Install with:npx skills add full-stack-skills/document-skills --skill api-doc-generator.
Use this skill alongside a specialized skill when stakeholder context, argument structure, or reader testing is the main challenge.
Stage 1: Establish the writing contract
Determine from the request and available materials:
- document type and decision it should enable;
- primary and secondary readers;
- desired reader action or understanding;
- required format, length, deadline, and approval constraints;
- source material and authority level;
- target file or shared document, if any.
Ask only questions whose answers materially change the document. Accept shorthand and unstructured context dumps.
Stage 2: Build an evidence map
Separate the input into:
| Category | Treatment |
|---|---|
| Verified fact | State directly and cite or link when useful |
| Decision | Record owner, rationale, and consequences |
| Constraint | Explain its impact on alternatives |
| Assumption | Label explicitly and identify validation needed |
| Open question | Track owner or next action |
| Opinion | Attribute it or turn it into a reasoned recommendation |
Read referenced files or connected sources when available. Do not claim access to integrations or tools that are not present. Never invent absent stakeholder positions.
Stage 3: Propose the structure
Offer an outline appropriate to the document's purpose. Explain only non-obvious ordering choices. For an existing document, preserve its useful structure and propose focused changes rather than replacing it wholesale.
Typical decision-document flow:
- Executive summary
- Context and problem
- Goals and non-goals
- Constraints and evidence
- Options considered
- Recommendation and rationale
- Risks and mitigations
- Rollout, validation, and ownership
- Open questions
Stage 4: Draft and refine
- Draft the highest-value sections first.
- Keep terminology consistent and define ambiguous terms once.
- Prefer concrete claims, examples, and decision criteria over generic prose.
- Preserve the user's voice and requested language.
- Flag evidence gaps inline with
待确认or an equivalent marker. - Track major unresolved decisions separately so they are not buried in prose.
- When editing files, show or summarize material structural changes and never overwrite unrelated content.
Stage 5: Reader testing
Test the document against the actual reader contract:
- Predict questions a new reader will ask.
- Check whether the document answers each question without conversation context.
- Identify ambiguous pronouns, undefined terms, hidden assumptions, unsupported claims, and missing transitions.
- Verify that the requested decision or action is obvious.
- Revise and repeat until no material reader gap remains.
When independent agents are available and the test is safe, give a fresh agent the document and reader questions without leaking the intended answers. Otherwise perform a cold-read pass using only the document text.
Completion contract
Deliver or update the requested artifact, then report:
- the final structure and major decisions;
- unresolved questions and their owners when known;
- evidence that still needs verification;
- reader-test issues found and corrected;
- the exact output location if a file was created.
FAQ
What does the doc-coauthoring skill do?
Collaboratively draft, revise, and reader-test substantial documentation such as proposals, RFCs, decision records, technical specifications, strategy documents, and cross-team plans. Use when the user needs help transferring context, shaping an argument, resolving gaps, iterating on an existing document, or validating whether a document works for readers. Use a more specialized document skill when the requested artifact is a product-doc suite, technical tutorial, or API reference.
How do I install doc-coauthoring?
Run npx skills add https://github.com/full-stack-skills/document-skills --skill doc-coauthoring in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/doc-coauthoring/ (personal) or .claude/skills/doc-coauthoring/ (project).
Which AI agents can use doc-coauthoring?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is doc-coauthoring safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains doc-coauthoring?
It is published by full-stack-skills in full-stack-skills/document-skills. It has 81 recorded installs.
More from full-stack-skills/document-skills
api-doc-generator
full-stack-skills/document-skills
Generate or update evidence-backed API documentation from OpenAPI specifications, framework routes, controllers, request/response models, validation rules, and tests. Use when the user explicitly asks for API or interface documentation, route inventory, endpoint reference, OpenAPI-derived docs, or synchronization between code and API docs. Supports OpenAPI-first projects and framework-specific discovery for Spring, FastAPI, NestJS, Express, and Gin; do not use for generic product documentation.
mermaid
full-stack-skills/document-skills
Open the skill to read its SKILL.md instructions.
full-stack-doc
full-stack-skills/document-skills
Scaffold, adapt, validate, and maintain example-rich full-stack product documentation: 10 product-level documents, 7 version documents, optional module PRD/Stitch/UI triplets, 5 delivery documents, and a detailed project README template family. Use when users ask to initialize a documentation repository, create product or version plans, write PRDs and architecture/UI documents, preserve and adapt detailed examples, audit document structure, or improve an existing product-docs tree, including Chinese requests such as 初始化文档、产品文档、写规划文档.
plantuml
full-stack-skills/document-skills
Open the skill to read its SKILL.md instructions.
processon-mindmap
full-stack-skills/document-skills
Design a ProcessOn-ready mind-map outline for ideas, requirements, knowledge systems, meeting notes, learning plans, or hierarchical analysis. Use when the user explicitly requests a ProcessOn mind map, editable mind map, or a hierarchical outline intended for ProcessOn. Do not trigger for ordinary diagrams, generic prose outlines, or Mermaid mind maps unless ProcessOn is requested.
processon-diagram-generator
full-stack-skills/document-skills
Generate ProcessOn-compatible editable diagrams and optionally render images through the ProcessOn API. Use when the user explicitly requests ProcessOn, hosted editable diagram output, or API-rendered flowcharts, swimlanes, sequences, architectures, ER diagrams, org charts, timelines, or infographics. Requires PROCESSONAPIKEY for remote generation. Prefer Mermaid for ordinary Markdown-native diagrams and PlantUML for strict UML/C4 source.
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.