aif-rules-check

Run a standalone read-only rules compliance gate against changed files or a git ref. Use when you need a dedicated project-rules check without a full review or verify pass.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/aif-rules-check/SKILL.md

Quality

Content

67%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 body is a well-sequenced, actionable read-only rules-gate workflow with concrete git commands, explicit verdict classification, and a clearly signaled one-level-deep reference for report structure. It is let down mainly by conciseness — repeated default restatements and a duplicate JSON example inflate the token budget.

Suggestions

Remove the restated defaults under Step 1 ("If `paths.rules_file` is missing..." / "If `git.base_branch` is missing...") since the default list above already covers them, or fold them into that list as parenthetical notes.

Drop the inline `aif-gate-result` JSON example in Step 5 and point to `references/RULES-CHECK-CONTRACT.md` instead, which already contains the identical block — this trims tokens and removes a drift risk.

Tighten Step 2.3's plan-resolution branching into a compact decision table rather than prose with repeated glob patterns and reserved-value caveats.

Dimension	Reasoning	Score
Conciseness	Quotes repeated default restatements ("If `paths.rules_file` is missing from config, default to `.ai-factory/RULES.md`...") and a Step 5 JSON example that duplicates the contract reference — mostly efficient but with several spots that could be tightened. Not a 4 because the redundancy and dense Step 2.3 plan-resolution globbing go beyond minor trimmable instances; not a 2 because it does not pad with concepts Claude already knows.	3 / 5
Actionability	Quotes executable commands like `git rev-parse --verify <argument>`, `git diff --cached --name-only`, and `git branch --show-current` plus a concrete `aif-gate-result` JSON block — mostly copy-paste-ready guidance. Not a 5 because some placeholders (`<argument>`, `<resolved-base-branch>`) and the multi-branch plan lookup leave minor gaps; not a 3 because the provided commands are real and runnable, not pseudocode.	4 / 5
Workflow Clarity	Quotes a clearly numbered Step 0–5 sequence with validation ("Validate it first: git rev-parse --verify") and an error-recovery fallback ("If invalid, ask: AskUserQuestion..."). Not a 5 because the read-only, non-destructive nature means the validate→fix→retry loop is light and some checkpoints are implicit; not a 3 because sequencing and ref-validation are explicitly present.	4 / 5
Progressive Disclosure	Quotes "Read `references/RULES-CHECK-CONTRACT.md` first" and "Treat it as the canonical source" — a well-signaled, one-level-deep reference (verified to exist) holding the report template, with the body acting as the workflow overview. Not a 5 because the inlined Step 5 JSON example partially duplicates the reference and the dense body could split out more; not a 3 because structure and signaling are clearly present.	4 / 5
	Total	15 / 20 Passed

Description

82%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 clearly and explicitly answers both what the skill does and when to use it, with third-person voice and an explicit Use-when trigger clause. It carves a distinct niche from sibling review/verify skills. Specificity is slightly limited because it describes one gated action rather than a suite of capabilities.

Dimension	Reasoning	Score
Specificity	Quotes "Run a standalone read-only rules compliance gate against changed files or a git ref" — names the domain and one concrete action (run a gate) with two input modes, but does not enumerate multiple distinct capabilities. Not a 4 because it lacks the several-specific-actions breadth of the anchor; not a 2 because the action and scope are concrete rather than minimal/generic.	3 / 5
Completeness	Quotes both an explicit what ("Run a standalone read-only rules compliance gate against changed files or a git ref") and an explicit when ("Use when you need a dedicated project-rules check without a full review or verify pass") with concrete trigger phrasing. Not below 5 because both halves are present, concrete, and explicit.	5 / 5
Trigger Term Quality	Quotes "rules compliance gate", "project-rules check", and "without a full review or verify pass" — good coverage of natural phrases a user would say. Not a 5 because common synonyms like "lint", "standards check", or "conventions" are absent; not a 3 because more than one natural term is present and well-targeted.	4 / 5
Distinctiveness Conflict Risk	Quotes "standalone read-only rules compliance gate" and "without a full review or verify pass" — explicitly carves a niche distinct from sibling /aif-review and /aif-verify skills, minimizing conflict risk. Not below 5 because the contrast is explicit and the trigger is narrow.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-rules-check/SKILL.md
Commit: ac92beb

Reviewed: 4 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.