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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

76%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.

A well-sequenced, highly actionable reliability-gate workflow with clear validation checkpoints and ready-to-use output templates. Its main weaknesses are verbosity in the skill-context subsection and inline policy content that would benefit from externalization.

Suggestions

Compress the skill-context subsection: consolidate the override-priority, CRITICAL, and Enforcement paragraphs into a single short rule stating that skill-context rules override SKILL.md defaults and must be verified against any output.

Move the detailed skill-context application rules into the referenced .ai-factory/skill-context file, keeping SKILL.md to a one-line mandatory-read pointer plus the conflict-resolution principle.

Reduce repetition between Step 4's confidence gate, the implementation guardrail, and the Artifact Ownership section, which restate the 'no guessing without 100 confidence' rule three times.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the extended skill-context subsection ("How to apply skill-context rules", the CRITICAL emphasis, and Enforcement paragraphs) reiterates the same override-priority idea several times and could be trimmed without losing clarity.	3 / 5
Actionability	Provides fully executable, copy-paste-ready output templates for both the 100-confidence and sub-100 cases, plus concrete classification categories and a hard rule tying unsupported claims to unknowns.	5 / 5
Workflow Clarity	Steps 0-5 are clearly sequenced with an explicit confidence gate acting as a validation checkpoint, a feedback condition (unknowns block answering), and a verification loop for changeable facts.	5 / 5
Progressive Disclosure	The body is reasonably sectioned, but it inlines a large skill-context policy block that reads like project-level configuration better kept in the referenced skill-context file, and the single mandatory reference is described narratively rather than as a clean navigational pointer.	3 / 5
	Total	16 / 20 Passed

Description

88%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.

A strong, third-person description that clearly communicates purpose and trigger conditions with natural user phrasing. It is concise yet complete, with only minor room to broaden distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists concrete behaviors ("evidence-based reasoning", "explicit uncertainty", "insufficient information instead of guesses") rather than vague abstractions, but stops short of a comprehensive multi-action inventory.	4 / 5
Completeness	Explicitly states both what it does (reliability gate enforcing evidence-based reasoning) and when to use it, with concrete trigger phrases and a high-stakes condition.	5 / 5
Trigger Term Quality	Includes several natural phrases users actually say ("be 100% sure", "no hallucinations", "only if verified", "grounded answer") plus the high-stakes condition, giving comprehensive trigger coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (reliability/anti-hallucination gate) with distinct triggers, though high-stakes conditions could overlap marginally with verification or review skills.	4 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-grounded/SKILL.md
Commit: e144f95

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.