CtrlK
BlogDocsLog inGet started
Tessl Logo

fact-check

Improve factual reliability while creating or reviewing a course or supplied content. Use when the user asks to fact-check, verify accuracy, reduce hallucinations, make a reliable course, or mentions 事实性错误、知识性错误、专业知识准确性、可靠性. During creation, checks the completed pages before delivery; on existing content, returns a short evidence-backed report and lets the user choose what to fix. Not for grammar, style, or layout. Combine with deep-research when current evidence is the course's main subject.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

The content is a well-structured, highly actionable instruction skill with clear sequencing and validation gates, achieving top marks for actionability and workflow clarity. The only friction is minor verbosity in the report-format section and the absence of any reference structure to push progressive disclosure to the top anchor.

Suggestions

Tighten the 'Give a short, readable review report' section by collapsing the repeated formatting rules into a compact template, reducing token cost without losing the required structure.

If the report-format spec or the finding-label conventions grow further, move them into a short reference file and link it one level deep, which would lift progressive_disclosure toward the top anchor.

Trim a few restated caveats (e.g., the approved-input protection is restated across 'Preserve approved inputs' and 'Let the user choose after a review') to improve conciseness.

DimensionReasoningScore

Conciseness

The body is dense with specific, earning guidance and avoids explaining concepts Claude already knows, but the detailed report-format specification (labels, three-bullet structure, ordering rules) is somewhat heavy and could be trimmed in places.

4 / 5

Actionability

Gives concrete, executable guidance throughout — named tool calls (list_scenes, read_stage with detail:'text', web_search, fetch_url, ask_user), specific budgets (6–8 searches, 3–8 findings), and exact option ids (fix_all, fix_confirmed, keep) — fully actionable for an instruction-only skill.

5 / 5

Workflow Clarity

Multi-step create and review workflows are clearly sequenced with explicit validation checkpoints (verify the shortlist, approved-input conflict check, ask_user approval gate) and a feedback loop (approve → load pro-editing → read source → edit → regenerate audio), so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

The skill is a single self-contained file with well-organized section headers and no nested references, so content is appropriately placed; with no bundle files to navigate it sits just below the top anchor, which expects clearly signaled one-level-deep references.

4 / 5

Total

18

/

20

Passed

Description

100%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.

The description is excellent: it states concrete capabilities, provides rich bilingual trigger terms, answers both what and when explicitly, and sets clear boundaries against neighbouring skills. No meaningful gaps to flag.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — fact-check, verify accuracy, reduce hallucinations, check completed pages before delivery, return an evidence-backed report, and let the user choose fixes — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (improve factual reliability, check pages, return an evidence-backed report) and 'when' (a 'Use when...' clause with concrete trigger phrases), meeting the top anchor.

5 / 5

Trigger Term Quality

Provides comprehensive natural trigger terms in both English (fact-check, verify accuracy, reduce hallucinations, make a reliable course) and Chinese (事实性错误、知识性错误、专业知识准确性、可靠性), covering synonyms a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (factual reliability of course content) and adds negative boundaries ('Not for grammar, style, or layout') plus explicit hand-off to deep-research, minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
THU-MAIC/OpenMAIC
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.