000-jeremy-content-consistency-validator
Validate messaging consistency across website, GitHub repos, and local documentation generating read-only discrepancy reports. Use when checking content alignment or finding mixed messaging. Trigger with phrases like "check consistency", "validate documentation", or "audit messaging".
74
56%
Does it follow best practices?
Impact
86%
1.17xAverage score across 6 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/data/000-jeremy-content-consistency-validator/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates its purpose, provides explicit trigger guidance, and occupies a distinct niche. Its main weakness is that the specific capabilities could be slightly more detailed (e.g., what kinds of discrepancies it detects, what the report format looks like), but overall it performs strongly across all dimensions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (messaging consistency across website, GitHub repos, local documentation) and the core action (validate/generate discrepancy reports), but doesn't list multiple concrete actions beyond validation and report generation. It's more specific than vague but not comprehensively listing distinct capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (validate messaging consistency across website, GitHub repos, and local documentation, generating read-only discrepancy reports) and 'when' (explicit 'Use when' clause plus 'Trigger with phrases' providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'check consistency', 'validate documentation', 'audit messaging', 'content alignment', 'mixed messaging'. These are phrases users would naturally say when needing this skill, with good variation coverage. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: cross-platform messaging consistency validation with read-only discrepancy reports. The combination of specific sources (website, GitHub repos, local docs) and the read-only constraint makes it unlikely to conflict with general documentation or content skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a skeleton with no actionable content. The instructions read like a high-level project description rather than concrete guidance Claude can follow. There are no code examples, no specific commands, no comparison logic, no report templates, and no concrete details about how to actually perform content consistency validation.
Suggestions
Replace the abstract instruction steps with concrete, executable guidance — e.g., specific WebFetch calls to retrieve website content, specific file glob patterns for local docs, and actual comparison logic or scripts.
Add a concrete example of what a discrepancy report looks like (even a partial template) so Claude knows the exact output format expected.
Include specific comparison criteria — what fields to compare, how to detect version mismatches, what constitutes a 'critical' vs 'warning' discrepancy — instead of vague directives like 'compare content systematically'.
Either inline the error handling and examples content or ensure the referenced files contain real, substantive guidance; currently the skill delegates all useful content to external files while providing nothing actionable itself.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content has some filler ('This skill provides automated assistance for the described functionality' is meaningless) and the Resources section lists vague topics with no links. However, it's not excessively verbose overall. | 2 / 3 |
Actionability | The instructions are entirely abstract and vague — 'Identify and discover all content sources', 'Extract key messaging', 'Compare content systematically' — with zero concrete code, commands, specific file patterns, comparison logic, or executable guidance. There is nothing copy-paste ready or specific enough to act on. | 1 / 3 |
Workflow Clarity | While steps are numbered, they are so vague as to be meaningless ('Compare content systematically across sources'). There are no validation checkpoints, no feedback loops, no specific tools or commands, and no error recovery guidance within the workflow itself. | 1 / 3 |
Progressive Disclosure | References to external files for errors and examples exist, which is good structure. However, the main content is so thin that there's essentially nothing useful in the skill itself — the references point to files that may or may not exist, and the Resources section lists topics with no actual links. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- majiayu000/claude-skill-registry
- Commit
d156cd1
- Reviewed
Table of Contents
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.