CtrlK
BlogDocsLog inGet started
Tessl Logo

fact-checker

Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 well-structured, actionable fact-checking workflow with strong validation checkpoints. Its main weaknesses are verbosity (duplicate checklists, padded auxiliary sections) and a monolithic single-file layout that underuses progressive disclosure.

Suggestions

Remove the duplicate checklist — keep either the Step-tracking block or the final Quality checklist, not both — to cut redundant tokens.

Trim or drop the promotional 'Next Step: Export Verified Content' section and consolidate 'Search best practices' / 'Special considerations' into the steps where they are actually applied.

Move the worked examples and detailed source-evaluation guidance into a one-level-deep reference file (e.g. references/examples.md) and link to it from the main workflow to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The ~290-line body is mostly efficient but padded: the progress checklist appears twice (Step list and Quality checklist), and sections like 'Search best practices', 'Special considerations', and the promotional 'Next Step: Export Verified Content' add tokens that could be trimmed.

2 / 3

Actionability

Provides concrete guidance — specific search-query patterns, a copy-paste comparison table and correction-report template, status codes, and an Edit-tool example — which is actionable for an instruction-oriented skill.

3 / 3

Workflow Clarity

Five clearly sequenced steps with a tracking checklist, an explicit user-approval checkpoint before destructive edits, and post-edit verification ('Verify all edits were applied successfully') provide the feedback loops the rubric requires.

3 / 3

Progressive Disclosure

The skill is a single ~290-line file with no bundle references; it is well-organized into sections, but substantial inline content (examples, search practices, special considerations) that could be split into one-level-deep reference files keeps it from a 3.

2 / 3

Total

10

/

12

Passed

Description

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.

The description is concise, action-oriented, and answers both what the skill does and when to use it with natural trigger terms. It is a strong, low-conflict description with no first/second-person voice issues.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Verifies factual claims', 'using web search and official sources', 'proposes corrections with user confirmation' — matching the anchor for several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Verifies factual claims…then proposes corrections with user confirmation') and when ('Use when the user asks to fact-check…') with an explicit trigger clause.

3 / 3

Trigger Term Quality

Natural user-facing terms — 'fact-check, verify information, validate claims, check accuracy, or update outdated information' — give good coverage of phrasings a user would actually say.

3 / 3

Distinctiveness Conflict Risk

A clear niche (verifying factual claims via web search with authoritative sources) with distinct triggers that are unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
daymade/claude-code-skills
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.