anthropic-docs-updater

Automated documentation update mechanism for anthropic-expert skill. Five-step workflow from update detection through documentation fetching and processing to skill integration and validation. Use when updating Anthropic documentation, checking for new releases, fetching latest docs, keeping anthropic-expert current, or synchronizing with Anthropic product changes.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%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 highly actionable, well-sequenced workflow with strong validation and rollback feedback loops and properly externalized scripts. Its main weakness is verbosity from redundant recap tables and best-practices restatements that re-cover ground already in the step-by-step sections.

Suggestions

Remove or collapse the Quick Reference tables (lines ~393-413) since they restate each step's time, automation level, and outputs already given in detail above — keep only a one-line command cheat sheet if anything.

Trim the Best Practices section (lines ~358-388); practices like "backup before updating" and "validate after updates" are already enforced by Steps 4 and 5, so the section adds tokens without new guidance.

Consider moving the large per-step example output block (lines ~100-120) and the detailed validation checklists into a reference file, keeping SKILL.md as a lean overview that points to scripts and a WORKFLOW.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — concrete commands, clear steps, no over-explanation of concepts Claude already knows — but the ~450 lines are padded with redundant recap material: the Quick Reference tables restate every step's time/automation/output and the Best Practices section restates guidance already embedded in the workflow.	3 / 5
Actionability	Fully executable throughout: copy-paste bash commands (`python scripts/check-updates.py --github`, `python scripts/update-skill.py --integrate processed/`), real script files verified to exist in ./scripts/, concrete file outputs, an example output block, and cron examples cover the common cases.	5 / 5
Workflow Clarity	A clearly numbered 5-step sequence with explicit validation checklists after every step, a PASS/FAIL decision point, and a rollback feedback loop in Step 5 (restore from backup on failure), satisfying the destructive/batch feedback-loop requirement rather than triggering the cap.	5 / 5
Progressive Disclosure	Well-structured with clear sections and executable detail correctly pushed to real bundle scripts (one level deep, referenced by command), but the SKILL.md itself is a long monolith whose Quick Reference recap duplicates step content rather than being trimmed or split into a reference file.	4 / 5
	Total	17 / 20 Passed

Description

83%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 that clearly states purpose and provides a robust set of natural trigger phrases in third person. It is held back only by somewhat abstract action wording and minor overlap risk with general documentation-sync skills.

Dimension	Reasoning	Score
Specificity	Names the domain (Anthropic docs maintenance for anthropic-expert) and several concrete workflow actions — "update detection", "documentation fetching and processing", "skill integration and validation" — but the actions are pipeline-shaped abstractions rather than the discrete, vivid verbs of a 5 anchor.	4 / 5
Completeness	Explicitly answers both what ("Automated documentation update mechanism... Five-step workflow from update detection... to skill integration and validation") and when ("Use when updating Anthropic documentation, checking for new releases...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Five natural trigger phrases ("updating Anthropic documentation", "checking for new releases", "fetching latest docs", "keeping anthropic-expert current", "synchronizing with Anthropic product changes") give good coverage with some synonym variation, though a few common phrasings a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Tied to a named skill (anthropic-expert) and Anthropic-specific sources, giving it a clear niche, but generic verbs like "fetching latest docs" could overlap with a general web-fetch or docs-sync skill.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/anthropic-docs-updater/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.