CtrlK
BlogDocsLog inGet started
Tessl Logo

aif-grounded

Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, actionable reliability-gate workflow with explicit validation gates and feedback loops. Its only weakness is conciseness: the skill-context preamble and restated core rule add tokens that could be tightened without losing meaning.

Suggestions

Trim Step 0's skill-context block: collapse the repeated emphatic reminders ("CRITICAL", "MANDATORY", "Do NOT ignore...") into a single concise statement that skill-context rules override these defaults and must be enforced.

State the 100/100 confidence rule once (either the intro or Step 4) and reference it rather than restating it, to remove redundancy.

Consider whether the skill-context preamble belongs inline or could move to a referenced file, keeping the core gate workflow as the lean spine of the body.

DimensionReasoningScore

Conciseness

Mostly efficient instruction content, but Step 0's skill-context block carries redundant emphatic padding ("CRITICAL", "MANDATORY", repeated "Do NOT ignore...") and the 100/100 rule is restated across the intro and Step 4.

2 / 3

Actionability

Provides concrete actionable guidance: a 3-way classification taxonomy, a hard rule converting unsupported claims to unknowns, and strict copy-paste-ready output templates with literal structure.

3 / 3

Workflow Clarity

Sequenced Step 0\u21925 with explicit validation checkpoints (Step 3 verify-or-refuse, Step 4 confidence gate) and feedback loops, plus a patch guardrail for the destructive case.

3 / 3

Progressive Disclosure

Well-organized into clear header sections with a single clearly-signaled, one-level-deep external reference (the skill-context file); no bundle files exist to evaluate against.

3 / 3

Total

11

/

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.

A concise, third-person description that names concrete capabilities, provides natural verbatim trigger phrases, and explicitly covers both what it does and when to use it. It is distinctive and unlikely to trigger for the wrong skill.

DimensionReasoningScore

Specificity

Lists multiple concrete enforced behaviors ("Forces evidence-based reasoning, explicit uncertainty, and \"insufficient information\" instead of guesses"), matching the multi-action anchor; it is not merely naming a domain.

3 / 3

Completeness

States what the skill does ("Reliability gate for answers") and includes an explicit "Use when..." trigger clause, so it clearly answers both what and when.

3 / 3

Trigger Term Quality

Quotes natural user phrases verbatim ("be 100% sure", "no hallucinations", "only if verified", "grounded answer"), giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (reliability/grounding gate) with distinctive, high-stakes-oriented triggers unlikely to collide with other skills' triggers.

3 / 3

Total

12

/

12

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
lee-to/ai-factory
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.