write-agent
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- Documentation
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: write-agent
description: Update, Synchronize, and Generate documentation for this repository. Used when the user needs to…
category: documentation
runtime: no special runtime
---
# write-agent output preview
## PART A: Task fit
- Use case: Update, Synchronize, and Generate documentation for this repository. Used when the user needs to auto update documentation: (1) Update @README.md (2) Update @AGENTS.md which @CLAUDE.md or @GEMINI.md links within Use when this capability is needed..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “README File / Startup Context Files” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Update, Synchronize, and Generate documentation for this repository. Used when the user needs to auto update documentation: (1) Update @README.md (2) Update @AGENTS.md which @CLAUDE.md or @GEMINI.md links within Use when this capability is needed.”.
- **02** When the source has headings, the agent prioritizes “README File / Startup Context Files” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “README File / Startup Context Files”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: write-agent
description: Update, Synchronize, and Generate documentation for this repository. Used when the user needs to…
category: documentation
source: tomevault-io/skills-registry
---
# write-agent
## When to use
- Update, Synchronize, and Generate documentation for this repository. Used when the user needs to auto update documenta…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “README File / Startup Context Files” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "write-agent" {
input -> user goal + target files + boundaries + acceptance criteria
context -> README File / Startup Context Files
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Auto Documentation
Auto updates Documentation and Context
README File
- Directory Structure: Update the README.md in the 'Directory Structure' section based on the up to date directory structure. The 'build' directory represents a separate cloned repositories outside of this one.
- Only required to include information relative to the repository directory structure
- Align all right hand comments to the same indent level for readability
- For Directories, only include important directories, it is not required to include all nested directories.
- Ensure to include the agent specific directories (.claude, .gemini, etc.) and top-level subdirectoriesfor discovery
- For Filenames, only include important filenames, it is not required to include all filenames.
- Ensure to include all agent specific files (AGENTS.md, CLAUDE.md, GEMINI.md, etc.) for discovery
- Quick Links: Update Quick Links based on the Markdown Headers as appropriate
- Docs Folder: Update files in the @./docs folder after major milestones and major additions to the project
- Links: Ensure that all links in the README.md are up to date and not broken.
- This includes links to files, directories, and external links.
Startup Context Files
All Context files (@CLAUDE.md, @GEMINI.md, etc.) should update the @AGENTS.md file, instead of their individual files. Based off the @README.md file at minimal. These context files should not be overly verbose, while still providing contextual information.
Source: akamlani/agent-skills — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review