Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

docs-health

Sterne4

Forks0

Aktualisiert8. Juli 2026 um 16:46

Analyze CLAUDE.md, AGENTS.md, rules, skills, plans, and docs for stale, broken, or conflicting context guidance. Use when docs may be outdated, contradictory, stale, misleading, or need a health check.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

samilozturk

samilozturk/artilens

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

Sonstige ComputerberufeInformatik- und Mathematikberufe·SOC 15-1299

SKILL.md

readonly

name	docs-health
description	Analyze CLAUDE.md, AGENTS.md, rules, skills, plans, and docs for stale, broken, or conflicting context guidance. Use when docs may be outdated, contradictory, stale, misleading, or need a health check.
allowed-tools	["Bash","Read","Agent"]

Docs Health

Run node "${CLAUDE_PLUGIN_ROOT}/scripts/run-artilens.mjs" docs-health --no-llm --data .claude/artilens/docs-health.data.json.
Relay the CLI's summary line to the user verbatim (score, finding count).
Start a background subagent with the Agent tool: subagent_type: general-purpose, model: sonnet, run_in_background: true. Prompt template: "Read <absolute path to docs-health.data.json> and ${CLAUDE_PLUGIN_ROOT}/references/artifact-authoring.md. Load the artifact-design skill, then author and publish an artifact with the Artifact tool. Page plan: score up front; findings table (file, kind, evidence); suggested fix list. All visual design decisions are yours."
Continue your own task. When the subagent finishes, relay the artifact URL to the user.

If contradiction candidates appear in the data JSON, inspect only the candidate lines before suggesting edits.

Mehr aus diesem Repository

gleiches Repository

agents

samilozturk/artilens

Visualize subagent, Agent tool, and delegated task activity from the current Claude Code session. Use when work was delegated or the user asks what agents/subagents did, what ran in the background, or how tasks were coordinated.

2026-07-084

artifacts

samilozturk/artilens

List, find, inspect, diff, resume, or update this project's locally registered artifacts. Use when the user references a previous artifact, asks what artifacts exist, wants artifact history, or wants to continue from an artifact.

2026-07-084

board

samilozturk/artilens

Create a draggable planning, kanban, roadmap, or backlog board artifact with copy-as-prompt feedback. Use for task ordering, project boards, sprint planning, prioritization, or moving cards between columns.

2026-07-084

commands

samilozturk/artilens

Catalog available slash commands, ArtiLens skills, plugins, and contextual recommendations. Use when the user asks what commands/tools/skills are available, what ArtiLens can do, or what to run next.

2026-07-084

compare

samilozturk/artilens

Create an option comparison artifact with tradeoffs and a recommendation. Use when the user wants to compare approaches, architectures, libraries, plans, implementation choices, pros/cons, or decision options.

2026-07-084

context-files

samilozturk/artilens

Inventory project context files — CLAUDE.md, AGENTS.md, rules, SKILL.md files, plans, and docs — with read-frequency from the current transcript. Use when the user asks what context is loaded, which files shaped the session, or before auditing stale or unused context files.

2026-07-084

name	docs-health
description	Analyze CLAUDE.md, AGENTS.md, rules, skills, plans, and docs for stale, broken, or conflicting context guidance. Use when docs may be outdated, contradictory, stale, misleading, or need a health check.
allowed-tools	["Bash","Read","Agent"]

Docs Health

Run node "${CLAUDE_PLUGIN_ROOT}/scripts/run-artilens.mjs" docs-health --no-llm --data .claude/artilens/docs-health.data.json.
Relay the CLI's summary line to the user verbatim (score, finding count).
Start a background subagent with the Agent tool: subagent_type: general-purpose, model: sonnet, run_in_background: true. Prompt template: "Read <absolute path to docs-health.data.json> and ${CLAUDE_PLUGIN_ROOT}/references/artifact-authoring.md. Load the artifact-design skill, then author and publish an artifact with the Artifact tool. Page plan: score up front; findings table (file, kind, evidence); suggested fix list. All visual design decisions are yours."
Continue your own task. When the subagent finishes, relay the artifact URL to the user.

If contradiction candidates appear in the data JSON, inspect only the candidate lines before suggesting edits.