source-evaluation

Use this skill when presenting information from external sources, citing research, or answering factual questions. Assess source credibility and recency before relying on it.

Quality

83%

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

100%Weight 40%Scale 1-3

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

The body is a model of brevity and actionability for a simple skill: concrete criteria, explicit red flags, and a clear best practice with no padding.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: the CRAAP acronym packs five criteria into a few lines, red flags and best practice are terse, and nothing restates what Claude already knows.	3 / 3
Actionability	Gives concrete decision rules ('Technology: < 2 years; science: check if superseded', 'triangulate ... across 2-3 independent sources') and a checklist of red flags a model can apply directly.	3 / 3
Workflow Clarity	A simple single-task skill (assess a source) that is clearly and well-organized with no risky multi-step operation requiring validation checkpoints.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references; content is split into clearly labeled sections (criteria, red flags, best practice) with nothing that should be split out.	3 / 3
	Total	12 / 12 Passed

Description

67%Weight 40%Scale 1-3

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

The description has a clear explicit trigger and states its purpose well, but its action language is somewhat abstract and its trigger terms could cover more natural variations a user would say.

Suggestions

Replace abstract phrasing with concrete actions, e.g. 'Evaluate source credibility using CRAAP criteria; flag unreliable, outdated, or biased sources before citing them.'

Add common natural trigger terms users would say, such as 'fact-checking', 'verifying claims', or 'reliable sources'.

Tighten the 'answering factual questions' trigger to reduce overlap with general research skills, e.g. scope it to 'evaluating or vetting sources before relying on them'.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('citing research', 'Assess source credibility and recency'), but the actions are abstract rather than the multiple concrete, specific actions of the 3-anchor.	2 / 3
Completeness	Has an explicit 'Use this skill when...' trigger clause and clearly states what it does ('Assess source credibility and recency before relying on it'), answering both what and when.	3 / 3
Trigger Term Quality	Includes some natural user terms ('citing research', 'factual questions', 'external sources') but misses common variations like 'fact-check', 'verify claims', or 'reliable source'.	2 / 3
Distinctiveness Conflict Risk	Source-credibility assessment is a clear niche, but 'answering factual questions' is broad enough to overlap with general research or web skills.	2 / 3
	Total	9 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aiming-lab/MetaClaw
Path: memory_data/skills/source-evaluation/SKILL.md
Commit: 922caf3

Reviewed: 9 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.