aif-distillation

Distill books, documents, folders, or URLs into compact, practical Agent Skills. Use when source material should become either one reusable skill package or a split set of focused skills, each with a concise SKILL.md plus detailed references and examples.

Quality

84%

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

81%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, instruction-oriented skill body with a clear validated workflow and good progressive disclosure via real reference files. The gaps are minor: some repetition across split-mode steps and a referenced examples path that is absent from the bundle.

Suggestions

Create the referenced examples/REQUESTS.md file (or remove the reference) so the signaled navigation resolves to real files and progressive disclosure reaches 5.

Consolidate the namespace-prefix and source-map-redaction rules stated in Steps 3, 4, and 5 into a single authoritative location to remove repetition and tighten conciseness.

Inline a short, concrete distillation excerpt (e.g., a worked before/after example) so the core actionability does not depend entirely on the referenced protocol files.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly lean, assuming Claude's competence without explaining what skills or distillation are, but repeats the namespace-prefix and source-map redaction rules across Steps 3, 4, and 5 in ways that could be tightened, keeping it just below fully efficient.	4 / 5
Actionability	Provides concrete executable guidance — the name regex `^[a-z0-9]+(?:-[a-z0-9]+)*$`, exact interpreter probes (`python3 --version`, `py --version`), and explicit output paths — but delegates the core distillation logic to referenced protocol files rather than giving copy-paste-ready steps inline.	4 / 5
Workflow Clarity	A clear 6-step sequence with explicit validation checkpoints (name validation, output-root containment, "validate usefulness" with a stated failure condition) and feedback loops (re-validate, merge-before-finishing), satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	SKILL.md is a clean overview with a dedicated "Required Supporting Guidance" section pointing one level deep to three real reference files, but the referenced `examples/REQUESTS.md` does not exist in the bundle, leaving a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

87%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 states both the capability and an explicit trigger clause with low conflict risk. The main limitation is that it elaborates one primary action rather than listing multiple distinct verbs, capping specificity at 4.

Dimension	Reasoning	Score
Specificity	Names the domain ("books, documents, folders, or URLs", "Agent Skills") and concrete output actions ("split set of focused skills, each with a concise SKILL.md plus detailed references and examples"), but centers on one primary verb (distill) rather than the multiple distinct actions of the 5 anchor, so it sits at 4 rather than 5.	4 / 5
Completeness	Explicitly answers both what ("Distill ... into compact, practical Agent Skills") and when ("Use when source material should become either one reusable skill package or a split set of focused skills") with a concrete "Use when..." trigger clause.	5 / 5
Trigger Term Quality	Good natural-term coverage ("source material", "skill package", "focused skills", "SKILL.md", "references and examples") that users would plausibly say, but misses common synonyms/extensions like "PDF" or "convert into a skill," placing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The distill-source-material-into-skills niche with single/split output triggers is specific and unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	13 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-distillation/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.