fact-check
Verify claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that MUST use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Triggers on "fact check", "verify claims", "check against primary sources", or when backlog items are marked UNVERIFIED.
Install with Tessl CLI
npx tessl i github:Jamie-BitFlight/claude_skills --skill fact-check99
Does it follow best practices?
Validation for skill structure
Discovery
100%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 an excellent skill description that excels across all dimensions. It provides specific actions and tools, includes natural trigger terms in an explicit 'Triggers on' clause, clearly distinguishes itself from similar skills by specifying its verification methodology (web lookups only, no training data), and produces well-defined outputs with citations.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Verify claims', 'spawns parallel verification agents', 'use WebFetch/WebSearch/gh', 'produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations'. Clear about what tools are used and what outputs are generated. | 3 / 3 |
Completeness | Clearly answers both what (verify claims against primary sources using web lookups, produce verdicts with citations) AND when (explicit 'Triggers on' clause with specific trigger phrases and conditions like 'backlog items marked UNVERIFIED'). | 3 / 3 |
Trigger Term Quality | Explicitly includes natural trigger terms users would say: 'fact check', 'verify claims', 'check against primary sources', 'UNVERIFIED'. These are intuitive phrases a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: fact-checking/verification with explicit rejection of training data recall, specific output format (VERIFIED/REFUTED/INCONCLUSIVE), and unique triggers like 'UNVERIFIED' status. Unlikely to conflict with general research or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill document that demonstrates strong technical writing. It provides clear, actionable guidance for fact-checking with explicit evidence rules, structured verdict formats, and well-defined workflows. The Chain of Verification requirement adds important validation, and the post-action steps ensure proper integration with the backlog system.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, avoiding explanations of concepts Claude already knows. Every section serves a purpose—evidence rules, claim extraction, verdict format—without padding or unnecessary context. | 3 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific verdict formats, exact agent spawn templates, structured report format, and explicit post-action commands (git add, commit, push). The claim classification and agent spawning instructions are copy-paste ready. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with mermaid diagrams showing claim extraction and wave execution flows. The Chain of Verification (CoVe) requirement adds explicit validation checkpoints, and post-actions include lint validation before commit. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (When to Use, Evidence Rules, Claim Extraction, etc.) and appropriate references to related skills at the end. Content is appropriately structured without being monolithic or requiring deep navigation. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- 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.