aif-loop

Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are reached. Use when user asks for iterative refinement, quality-gated generation, or "generate -> critique -> refine" loops.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

The body is highly actionable with a clearly sequenced, validation-gated workflow and well-organized one-level references. Its only weakness is conciseness: structural redundancy (phases restated three times; two 'Step 0' sections) prevents it from being fully lean.

Suggestions

Consolidate the phase descriptions so each phase is defined once — the Core Idea list, Step 3.1, and Step 4 repeat the same six phases; reference the canonical list instead.

Rename or merge the two 'Step 0' sections ('Load Config' and 'Load Context') into a single clearly numbered preamble to remove label collision and improve navigability.

Tighten the JSON examples (e.g. the full run.json block) to the minimal fields needed for each instruction point, or move the complete schema to a reference file, to reduce inline token weight.

Dimension	Reasoning	Score
Conciseness	The ~485-line body is mostly efficient and assumes Claude's competence, but contains real redundancy: the six phases are described three times (Core Idea, Step 3.1, Step 4) and two separate 'Step 0' sections (Load Config and Load Context) blur the structure, so it could be tightened rather than earning the lean/efficient top anchor.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance — exact JSON schemas, file paths, bash commands, event names, and field names — fully executable rather than abstract.	3 / 3
Workflow Clarity	Multi-step phases are clearly sequenced with explicit validation checkpoints (mandatory user confirmations, phase-output validation, retry-once on phase_error, stagnation tracking, and corrupted-run.json recovery).	3 / 3
Progressive Disclosure	SKILL.md is an overview and externalizes separable detail to one-level-deep, clearly signaled references — references/CRITERIA-TEMPLATES.md, PHASE-CONTRACTS.md, and RULE-SCHEMA.md — all of which exist as real bundle files.	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.

The description is specific, complete, and distinctive, with concrete phase names and an explicit 'Use when' trigger. It uses third-person voice and avoids fluff, hitting the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists concrete actions — six named phases (PLAN, PRODUCE\|\|PREPARE, EVALUATE, CRITIQUE, REFINE) plus 'improve an artifact until quality gates pass or iteration limits are reached' — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (a multi-iteration loop with defined phases) and 'when' via a clear 'Use when user asks for...' trigger clause.	3 / 3
Trigger Term Quality	Includes several natural phrases a user would say — 'iterative refinement', 'quality-gated generation', and 'generate -> critique -> refine' — giving good coverage rather than a single generic keyword.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (strict phase-contracted Reflex Loop with quality gates) with distinctive triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-loop/SKILL.md
Commit: 4b943ec

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.