ワンクリックでManusで任意のスキルを実行

doc-gardener

スター4

フォーク0

更新日2026年2月20日 14:45

Keep repository documentation accurate and agent-legible through drift detection and deterministic fixes. Use when asked to scan docs for stale content, broken links, metadata/nav drift, API coverage gaps, or to run recurring documentation gardening in on-demand or scheduled maintenance loops.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

JanuaryLabs

JanuaryLabs/deepagents

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Doc Gardener

Run this skill to maintain documentation integrity with deterministic checks and safe autofixes.

Workflow

Run scripts/run.ts in on-demand or scheduled mode.
Detect API drift, behavior drift, and docs integrity issues.
Apply safe fixes for links, anchors, and meta.json page drift.
Produce machine-readable and human-readable reports under artifacts/doc-gardener/<timestamp>/.
For scheduled mode, include a single batch PR summary grouped by package/domain.

Commands

node .codex/skills/doc-gardener/scripts/run.ts --mode on-demand --base origin/main --head HEAD --apply
node .codex/skills/doc-gardener/scripts/run.ts --mode scheduled --apply

Optional flags:

--report-dir <path>: custom report directory
--skip-verify: skip Nx lint/test/build verification gates

Notes

--apply defaults to true.
On-demand mode uses nx affected gates.
Scheduled mode uses nx run-many gates.
Semantic/API narrative changes are left as unresolved follow-ups with evidence.

For detailed policy and sequence, read:

references/rules.md
references/workflow.md

このリポジトリの他の Skills

同じリポジトリ

agent-testing

JanuaryLabs/deepagents

Test code built on AI SDK v7 using its real `ai/test` utilities and V4 provider protocol. Use whenever writing, fixing, reviewing, or migrating tests around AI SDK agents, `generateText`, `streamText`, structured output, tools, embeddings, image/speech/transcription/reranking/video models, provider registries, or simulated streams. Trigger for phrases such as "test my agent", "mock the model", "fake the stream", "simulate a tool call", "test retry logic", "inspect the system prompt", "my streaming test hangs", or "empty result.text", even when the user does not explicitly name AI SDK. This skill is v7-only: remove V3 fixtures and custom helpers that duplicate `ai/test`.

2026-07-124

reuse

JanuaryLabs/deepagents

Analyze a target piece of code and propose how to make it reusable across the rest of the codebase. Walks through phases — understand → survey → design → migration plan — and only edits code after the user approves the plan. Codebase-agnostic. Run only when the user explicitly invokes it (e.g. `/reuse`, "make this reusable", "extract this", "find duplicates of this").

2026-04-294

text2sql-system-prompt-updater

JanuaryLabs/deepagents

Update the Text2SQL system prompt in a generalizable, non-overfit way using failure-pattern driven evaluation loops. Use when SQL generation quality regresses or specific failure classes repeat.

2026-02-244

commit

JanuaryLabs/deepagents

Write conventional commit messages with type, scope, and subject when the user wants to commit changes or save work.

2026-02-224

write-docs

JanuaryLabs/deepagents

Generate documentation for a package by analyzing source code. Use when the user wants to write, create, or generate new documentation pages for a package from scratch.

2026-02-214

update-docs

JanuaryLabs/deepagents

Update documentation based on code changes since last push. Use when the user wants to update, sync, or refresh documentation to match recent code changes across packages.

2026-02-204

name	doc-gardener
description	Keep repository documentation accurate and agent-legible through drift detection and deterministic fixes. Use when asked to scan docs for stale content, broken links, metadata/nav drift, API coverage gaps, or to run recurring documentation gardening in on-demand or scheduled maintenance loops.

Doc Gardener

Run this skill to maintain documentation integrity with deterministic checks and safe autofixes.

Workflow

Run scripts/run.ts in on-demand or scheduled mode.
Detect API drift, behavior drift, and docs integrity issues.
Apply safe fixes for links, anchors, and meta.json page drift.
Produce machine-readable and human-readable reports under artifacts/doc-gardener/<timestamp>/.
For scheduled mode, include a single batch PR summary grouped by package/domain.

Commands

node .codex/skills/doc-gardener/scripts/run.ts --mode on-demand --base origin/main --head HEAD --apply
node .codex/skills/doc-gardener/scripts/run.ts --mode scheduled --apply

Optional flags:

--report-dir <path>: custom report directory
--skip-verify: skip Nx lint/test/build verification gates

Notes

--apply defaults to true.
On-demand mode uses nx affected gates.
Scheduled mode uses nx run-many gates.
Semantic/API narrative changes are left as unresolved follow-ups with evidence.

For detailed policy and sequence, read:

references/rules.md
references/workflow.md