aif-rules

Add project-specific rules and conventions to the configured RULES.md artifact. Each invocation appends new rules. These rules are automatically loaded by /aif-implement before execution. Use when user says "add rule", "remember this", "convention", or "always do X".

Quality

77%

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/SKILL.md

Quality

Content

63%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-structured, actionable workflow for managing project rules with clear modes and templates. It is somewhat verbose with heavy emphasis and keeps all content in a single monolithic file rather than progressively disclosing detail.

Suggestions

Trim redundant emphasis in Step 0.1 (remove repeated CRITICAL/MANDATORY capitals and restated 'skill-context rule wins' lines) to improve conciseness.

Move the Rules Hierarchy and skill-context override rules into a references/ file (e.g. HIERARCHY.md) and link to it from the body to improve progressive disclosure.

Add an explicit validate→fix→retry checkpoint for Mode C config.yaml registration (e.g. re-read config after edit to confirm rules.<area> resolved correctly) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes padded emphasis ('CRITICAL', 'MANDATORY', repeated 'the skill-context rule wins') and a Rules Hierarchy section that re-states priority already implied by the workflow; could be tightened without losing meaning, fitting the 3 anchor rather than the lean 4.	3 / 5
Actionability	Provides concrete, copy-paste-ready markdown templates, exact Glob/Edit operations, and AskUserQuestion option blocks, but a few steps ('Parse area name', 'Check if area file exists') remain slightly abstract, placing it just below fully executable 5.	4 / 5
Workflow Clarity	Clear sequenced steps (Step 0 → 0.1 → 1 → modes → 2/3/4) with existence checks, duplicate checks, and an explicit STOP after Mode C; minor validation gaps keep it below the explicit validate→fix→retry 5 anchor.	4 / 5
Progressive Disclosure	Well-sectioned internally but ~245 lines with no bundle files and no one-level-deep references; content like the verbose skill-context block and hierarchy could live in a reference file, matching the 'some structure, content that should be separate is inline' 3 anchor.	3 / 5
	Total	14 / 20 Passed

Description

91%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 description that clearly states purpose, behavior, and concrete trigger phrases in third person. The only weakness is mild overlap risk from the generic 'remember this' trigger.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Add project-specific rules and conventions to the configured RULES.md artifact', 'Each invocation appends new rules', 'automatically loaded by /aif-implement before execution' — with only minor coverage gaps, fitting the 'lists several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('Add project-specific rules and conventions... Each invocation appends new rules') and when ('Use when user says...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Provides natural user phrases — 'add rule', 'remember this', 'convention', 'always do X' — covering multiple variations a user would actually say, matching the comprehensive natural-term anchor.	5 / 5
Distinctiveness Conflict Risk	Mostly distinct via the RULES.md artifact and /aif-implement coupling, but 'remember this' is a generic phrase with minor overlap risk against general memory/note skills, so it sits just below the minimal-conflict 5.	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-rules/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.