add-doc-updater

Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-orchestrated, highly actionable multi-phase skill with strong validation checkpoints, error-recovery loops, and a real one-level-deep template reference. Its main weakness is token efficiency: rationale lines explaining tools Claude already knows, per-variable metadata, and a redundant workflow diagram inflate the body without adding guidance value.

Suggestions

Drop the 'Rationale:' lines under Phase 3 steps and the per-variable 'Used for'/'Example' annotations in Phase 0; keep defaults and constraints only.

Remove or shrink the mermaid flowchart — the section headings already encode the phase sequence, and the bundled template contains its own workflow diagram covering the same flow.

Trim Phase 5a/5b markdown/text blocks to the minimal insertable snippet so the integration section reads as a lean overview pointing to the template for detail.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, but includes trimmable padding: 'Rationale:' lines explaining what ruff/mypy/prek do (which Claude already knows), per-variable 'Used for' annotations in Phase 0, and a mermaid diagram that largely restates the section headings that follow it.	3 / 5
Actionability	Concrete, executable bash commands throughout (ruff format/check, mypy, pyright, 'uv run prek run --files', the 7-point validation commands) and precise delegation instructions with a real template file. Falls short of copy-paste-ready because {script-path}/{target-path} placeholders must be substituted and a few steps are directives ('Read 3-5 random markdown files') rather than commands.	4 / 5
Workflow Clarity	Exemplary sequencing: six clearly numbered phases, each quality gate gating the next, an explicit 7-point validation checklist with expected outcomes, defined failure loops back to Phase 1 with error context, and an escalation rule after 3+ failed iterations. Matches the top anchor with feedback loops and checklists.	5 / 5
Progressive Disclosure	Good structure: well-organized phase sections and a single clearly signaled, existing, one-level-deep reference (references/doc-updater-template.md, verified present). Minor gaps: the mermaid workflow diagram duplicates the template's own workflow overview, and some Phase 0/5 detail could live in the reference to keep SKILL.md a leaner overview.	4 / 5
	Total	16 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete multi-action capability statement in third person with an explicit 'Use when' trigger clause. Trigger terms are good but lack synonym breadth (e.g., offline/cached docs, specific doc-source examples), which is the only dimension below the top anchor.

Suggestions

Broaden trigger terms with natural synonyms, e.g., 'Use when adding offline, cached, or auto-synced reference documentation (e.g., GitLab CI, glab CLI docs) to a plugin or skill.'

Include the concrete doc-source examples already present in the bundled template to sharpen distinctiveness from static-reference skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh' plus 'Collects template variables, then delegates implementation through 5-phase workflow' — comprehensive and specific, matching the top anchor.	5 / 5
Completeness	Clearly answers 'what' (creates sync script, downloads/processes/caches docs, 5-phase workflow) AND 'when' with an explicit trigger clause: 'Use when adding auto-updating reference documentation to plugins or skills.' Both are concrete, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Good natural keywords ('documentation updater', 'sync', 'auto-updating reference documentation', 'plugins or skills') but misses common variations users might say, such as 'offline docs', 'cached documentation', or naming specific doc sources like GitLab. Not quite comprehensive synonym coverage as required for a 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (adding an auto-updating doc pipeline to a skill) with distinct triggers, but 'any Claude skill' plus generic 'reference documentation' wording leaves minor overlap risk with skills that add static reference files. Mostly distinct, fitting the 4 anchor.	4 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: Jamie-BitFlight/claude_skills
Path: plugins/plugin-creator/skills/add-doc-updater/SKILL.md
Commit: 3e0b2af

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.