CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

70%

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

Fix and improve this skill with Tessl

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

Quality

Content

60%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 core gate workflow is well-engineered: executable commands, explicit fallback and validation logic, and a clean single-reference split for the canonical contract. The main weakness is token efficiency — generic interaction policy, repeated statements, and duplicated reference content inflate the body well beyond what the task requires.

Suggestions

Trim or move the 'Runtime-aware questions' and 'Shared project skill-context' sections into a shared reference or the linked contract file; they are generic cross-skill policy that consumes roughly a third of the body without being specific to this gate.

Remove verbatim duplicates: the 'Only return FAIL when an explicit hard rule is clearly violated' sentence, the second git.base_branch fallback explanation in Step 1, and the closing 'Schema reminder' line that repeats the JSON example and bullet list in Step 5.

Extract the dense Step 2.3 plan-resolution logic (branch stem, sequential/slug formats, ultra marker counting) into a reference file like references/PLAN-RESOLUTION.md, keeping a two-line summary in the body, and add one worked example of tying a rule violation to a diff hunk in Step 3.

DimensionReasoningScore

Conciseness

Noticeably verbose: a long generic question-asking policy section, cross-skill meta policy, and verbatim repetitions (the FAIL rule stated twice, the git.base_branch fallback explained twice, a schema reminder repeating the JSON example) — anchor 2, not 3, since more than 'some' tightening is needed.

2 / 5

Actionability

Concrete executable git commands ('git rev-parse --verify <argument>', 'git diff --cached --name-only'), explicit config paths with defaults, and an exact aif-gate-result JSON example — anchor 4 rather than 5 because the AskUserQuestion block is a sketch and there is no worked example of matching a rule to a diff hunk.

4 / 5

Workflow Clarity

Clear step sequence with input validation ('Validate it first'), fallback chains (staged → working tree → branch diff), and WARN de-escalation rules with evidence requirements — anchor 4 rather than 5 because Step 2.3's plan-resolution bullets are convoluted and hard to follow.

4 / 5

Progressive Disclosure

One real, clearly signaled, one-level-deep reference ('Read references/RULES-CHECK-CONTRACT.md first') that appropriately owns the canonical contract — anchor 4 rather than 5 because the body still inlines generic cross-skill policy, the dense plan-resolution logic, and duplicated contract content.

4 / 5

Total

14

/

20

Passed

Description

70%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 solid description with an explicit 'Use when' clause, a clear read-only rules-gate niche, and a deliberate contrast against related review/verify skills. Its main limitations are modest action specificity and a trigger clause that is somewhat circular rather than scenario-based.

DimensionReasoningScore

Specificity

Names the domain ('rules compliance gate') and 1-2 concrete actions ('Run a standalone read-only... gate against changed files or a git ref') but does not enumerate several specific operations, matching anchor 3 rather than 4.

3 / 5

Completeness

Explicitly answers both what ('Run a standalone read-only rules compliance gate...') and when ('Use when you need a dedicated project-rules check...'), but the trigger clause restates the what rather than giving concrete trigger phrases — anchor 4, not 5.

4 / 5

Trigger Term Quality

Includes natural phrases users would say ('rules compliance', 'project-rules check', 'changed files', 'git ref') with good coverage, though common synonyms like 'conventions', 'standards', or 'policy' are missing — anchor 4, not 5.

4 / 5

Distinctiveness Conflict Risk

The contrast 'without a full review or verify pass' explicitly distinguishes it from sibling skills, giving a mostly distinct niche with only minor overlap risk against general code-review skills — anchor 4.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

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.