aif

Set up agent context for a project. Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers. Use when starting new project, setting up AI context, or asking "set up project", "configure AI", "what skills do I need".

Quality

88%

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 thorough, highly actionable setup skill with strong validation and feedback loops for its destructive/batch operations. Its main weakness is repetition of the security-scan recipe across three sections and the inlining of sizable templates that could live in reference files.

Suggestions

Consolidate the security-scan procedure into one authoritative section and have later occurrences reference it, rather than re-stating the full Level 1 / cleanup-blocked-skill recipe three times.

Move the large MCP runtime-format matrix and/or the AGENTS.md template into dedicated reference files under references/ and link to them, reducing the SKILL.md body length.

Trim explanatory prose that restates what a file is for (e.g. 'This file helps any AI agent...') since Claude already understands these conventions.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but the security-scan recipe (Level 1 scan + cleanup-blocked-skill exit-code handling) is repeated with near-identical detail in the CRITICAL section, the Skill Acquisition Strategy block, and Mode 1 Step 8, and some template prose (e.g. what AGENTS.md is 'for') could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready commands throughout — 'npx skills search/install', 'python3 .../security-scan.py <path>', 'node .../update-config.mjs --template ... --target ... --payload ...', 'mkdir -p .ai-factory' — with concrete exit-code handling and a JSON payload shape, covering the common cases fully.	5 / 5
Workflow Clarity	Each mode is a clearly numbered sequence with explicit validation checkpoints and feedback loops: two-level security scan with Exit 0/1/2 branching and cleanup, 'Both levels must pass', and 'If the helper reports an unsafe structure... STOP. Do not fall back to free-form YAML' — meeting the score-5 anchor for destructive/batch operations.	5 / 5
Progressive Disclosure	Structure is good with clear section headers, and references that exist are one level deep and real (update-config.mjs and config-template.yaml in references/ are both cited); however large blocks like the MCP runtime-format matrix and the AGENTS.md template are inlined rather than split into reference files, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

96%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 four concrete capabilities and pairs them with multiple natural trigger phrases. It is highly specific and complete, with only minor overlap risk on the broadest 'set up project' wording.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions — 'Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers' — giving comprehensive coverage of what the skill does, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (set up agent context: analyze stack, install skills, generate skills, configure MCP) and 'when' ('Use when starting new project, setting up AI context, or asking...') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Includes natural user phrasings and synonyms such as 'starting new project', 'set up project', 'setting up AI context', 'configure AI', and 'what skills do I need', which are exactly what a user would say; comprehensive coverage of natural terms.	5 / 5
Distinctiveness Conflict Risk	The AI-context/agent-config framing and triggers like 'configure AI' and 'what skills do I need' carve a distinct niche, but 'set up project' and 'starting new project' are broad enough to risk minor overlap with general project-scaffolding skills, so it sits just below the score-5 anchor.	4 / 5
	Total	19 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (786 lines); consider splitting into references/ and linking	Warning
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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	12 / 16 Passed

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