KS
Killer-Skills

docs-sync — Categories.community

v1.0.0
GitHub

About this Skill

Perfect for CLI-based Agents needing to maintain consistent and up-to-date documentation across multiple files. CLI sandbox for experimenting with LLM agents, tool-calling, and evals.

valuecodes valuecodes
[0]
[0]
Updated: 2/7/2026

Quality Score

Top 5%
45
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add valuecodes/cli-agent-sandbox

Agent Capability Analysis

The docs-sync MCP Server by valuecodes is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Perfect for CLI-based Agents needing to maintain consistent and up-to-date documentation across multiple files.

Core Value

Empowers agents to synchronize documentation files, including README.md, AGENTS.md, and .codex/** configurations, using a CLI sandbox for experimenting with LLM agents, tool-calling, and evaluations, ensuring consistent references and avoiding stale data through Markdown file updates.

Capabilities Granted for docs-sync MCP Server

Updating documentation files in bulk
Propagating changes to relevant doc files
Maintaining consistency across README.md, AGENTS.md, and CLAUDE.md

! Prerequisites & Limits

  • Requires access to documentation files
  • Limited to Markdown file formats
  • Single-package repository only
Project
SKILL.md
2.0 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Docs Sync

Keep documentation consistent and up-to-date for this single-package repo. When updating commands, paths, or tool behavior, propagate changes to all relevant doc files to avoid stale references.

Scope

Documentation files to consider:

  • README.md
  • AGENTS.md
  • CLAUDE.md (symlink to AGENTS.md, do not edit directly)
  • .codex/** (Codex agent configs and skills)
  • Any new doc-like Markdown files added later

Workflow

  1. Find doc files: Scan for all documentation files listed in Scope.
  2. Update references consistently: When changing a command, path, or pattern, update ALL occurrences across all doc files. Never partially update.
  3. Add/update explanations: When changing a command or config, add or update a short explanation of what it does and why.
  4. Run formatter: Execute pnpm format if you touched Markdown or config files that are formatted.
  5. Run validation (if needed): If documentation changes include code or tooling changes, run pnpm lint, pnpm typecheck, and pnpm test. Skip these when edits are doc-only.
  6. Summarize changes: Report files changed and flag anything that needs human review.

Guidelines

  • Keep docs concise and scannable
  • Use consistent terminology across all files
  • Prefer examples over lengthy explanations
  • Update version numbers/dates if present
  • Remove obsolete sections rather than leaving stale content
  • When adding new commands, include both the command and a brief explanation
  • Do not introduce instructions that conflict with AGENTS.md
  • Do not edit CLAUDE.md directly; update AGENTS.md instead
  • Mermaid: wrap node text in quotes like A["Label"] and B{"Question?"} to avoid parse issues with punctuation

Output Requirements

Always finish with a summary:

  • Files changed: List of documentation files modified
  • What to review: Any changes that need human verification (e.g., explanations that may need refinement, removed sections)
  • Validation status: Commands run, or explicitly note what was skipped

Related Skills

Looking for an alternative to docs-sync or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication