Skill

doc-update

Update knowledge documents for target audience. Adjusts depth, adds context, and maintains documents as living documentation.

Install

npx claudepluginhub t-hasuike/clysis --plugin legacy-knowledge

Tool Access

This skill uses the workspace's default tool permissions.

Preview

> This is a generic skill from [CLysis](https://github.com/t-hasuike/CLysis).

SKILL.md

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

139.1k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

smart-explore

Performs token-optimized structural code search using tree-sitter AST parsing to discover symbols, outline files, and unfold code without reading full files.

claude-mem

65.8k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitApr 6, 2026

Actions

View Source View Plugin View on GitHub View README

/doc-update -- Document Update & Audience Adaptation Skill

This is a generic skill from CLysis. Terminology can be customized via config/terminology.md.

Overview

Update existing knowledge documents to match the needs of a specific audience. Maintains documents as living documentation by comparing current code state against documented state and updating accordingly.

When to Use

After /current-prd produces new findings that need to be integrated
When onboarding a new team member (generate audience-appropriate docs)
Periodic document freshness checks
When code changes make existing documentation outdated

Target Audiences

Audience	Depth	Focus
`developer`	Deep (code-level)	Implementation details, API contracts, database schemas, gotchas
`pm`	Medium (feature-level)	Business rules, user flows, feature boundaries, constraints
`onboarding`	Progressive (guided)	Start with overview, link to details. "Read this first" ordering

Workflow

Step 1: Current State Assessment

Read the target knowledge file(s)
Check version/last-updated date
Compare against current codebase (use Serena for symbol verification)
Identify gaps: documented but changed, exists but undocumented, documented but removed

Step 2: Audience Adaptation

Based on target audience, adjust:

Level of detail: developer gets code paths, PM gets business rules
Terminology: developer uses class/method names, PM uses feature names
Examples: developer gets code snippets, PM gets user scenarios
Navigation: onboarding gets "read next" links, developer gets API reference

Step 3: Update & Report

Update the target file(s) with new/corrected information
Maintain version history in the file
Report changes to the user (what was added, removed, corrected)

Living Document Rules

Every update increments the version number
Last-updated date is always current
Removed content is noted in version history (not silently deleted)
Cross-references to other knowledge files are verified on each update
Stale content (>30 days without verification) is flagged with [NEEDS VERIFICATION]

Output Rules

Update knowledge/ files directly (this skill is authorized to modify knowledge/)
State observations only. No modification proposals for application code
Subject-first rule: always specify "whose/what's" for domain terms

Strict F002 compliance: Leader does not personally update knowledge/. Delegate execution to workers.

Language and Tone

Clear, professional reporting with business etiquette. Clearly state OK/NG, explicitly state what is unclear.

Integration with Existing Skills

Existing Skill	Relationship
`/current-spec`	Provides bulk findings that doc-update integrates
`/doc-organize`	Handles reports/ → knowledge/ promotion. doc-update handles knowledge/ maintenance
`/doc-check`	Diagnoses issues. doc-update executes fixes

I/O Specification

INPUT

Type	Content	Required
Target audience	`developer`, `pm`, or `onboarding`	Required
Scope	File path or directory within knowledge/	Optional (default: all knowledge/)

OUTPUT

Type	Format	Destination
Updated documents	Markdown (in-place update)	`knowledge/` (direct modification)
Change report	Markdown (diff summary)	stdout (session report)

Downstream Skills (Pipeline)

Skill	Condition
`/doc-check`	Post-update integrity verification

Quality Checklist

Version number incremented
Last-updated date set to current
Cross-references verified (no broken links)
Audience-appropriate depth applied
No modification proposals for application code
Stale content flagged where applicable