aif-transfer

Transfer reusable prevention lessons from another AI Factory project into the current project's skill-context through /aif-evolve. Use when building a similar project and you want to avoid problems already captured in another project's patches without copying or revealing that project's identity, paths, or identifiers.

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-transfer/SKILL.md

Quality

Content

70%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-engineered instruction-only workflow with an exemplary validation structure: sequenced steps, preflight and post-write privacy verification, and error-recovery loops. Its weaknesses are repetition of the privacy denylist across sections and a fully monolithic single-file layout with no progressive disclosure of detail into reference files.

Suggestions

Factor the repeated source-identifier denylist (currently stated in the Privacy Contract, Step 4, and Steps 5/7) into a single canonical list referenced by each check, cutting roughly 20-30 lines of duplication.

Move the config-resolution details and defaults (paths.*, language.*, rules.* key handling) into a references/config.md file and keep only the essential keys and defaults inline, so SKILL.md stays a lean operational overview.

Inline a brief summary of the /aif-evolve steps being reused (stale-rule checks, gap analysis, proposal format) or point to their exact section anchors, so the skill remains actionable when the evolve skill's content is not already in context.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and avoids concept explanations, but the source-identifier denylist is repeated nearly verbatim across the 'Non-Negotiable Privacy Contract', Step 4, and Steps 5/7, and the config-resolution defaults block could be tightened.	3 / 5
Actionability	Gives concrete, executable guidance — exact usage examples, config keys with defaults, 'experience-NNN' labeling, and the exact metadata string 'Based on: N analyzed prevention candidates' — but delegates core mechanics to /aif-evolve ('Reuse its stale-rule checks, gap analysis, proposal format') without defining them.	4 / 5
Workflow Clarity	Steps 0–7 are clearly sequenced with explicit validation checkpoints and feedback loops: 'On any match, rewrite or remove the affected candidate and repeat the full preflight' and 'If a leak is found, remove or rewrite it immediately and re-check all changed files', plus explicit stop conditions throughout.	5 / 5
Progressive Disclosure	No bundle files exist and everything is inline in one ~270-line SKILL.md; sections are well-organized, but content that could live in reference files (the privacy denylist, config-resolution defaults) is inlined with no references offered.	3 / 5
	Total	15 / 20 Passed

Description

80%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 and explicitly states both capability and usage conditions in third person. Its only weakness is trigger-term coverage, which is adequate but jargon-heavy and lacks natural synonym variations.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Transfer reusable prevention lessons… into the current project's skill-context through /aif-evolve' and anonymization 'without copying or revealing that project's identity, paths, or identifiers' — but omits the relevance-gating and approval mechanics, so coverage has minor gaps.	4 / 5
Completeness	Explicitly answers both what ('Transfer reusable prevention lessons… through /aif-evolve') and when ('Use when building a similar project and you want to avoid problems…') with concrete trigger conditions.	5 / 5
Trigger Term Quality	Includes some natural phrases ('building a similar project', 'avoid problems already captured') but leans on domain jargon ('prevention lessons', 'skill-context', 'patches') and misses common synonyms or variations a user might say.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (cross-project anonymized lesson transfer within AI Factory via /aif-evolve) with triggers unlikely to fire for any other skill.	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-transfer/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.