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

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.

A thorough, highly actionable orchestration skill with strong workflow sequencing and good use of external references. Its main weakness is conciseness: security-scanning instructions and command-selection details are repeated across multiple sections, inflating the token budget without adding new information.

Suggestions

Consolidate the security-scan and cleanup-helper instructions into a single canonical section and reference it from Mode 1 Step 8 and the Skill Acquisition Strategy instead of restating the full procedure each time.

Tighten the Language Resolution section by collapsing the resolution-order list and the six-step workflow into a compact table or checklist; much of the prose reiterates the priority order twice.

Move the lengthy MCP runtime-format matrix and per-runtime wrapper examples into a references file (e.g. references/mcp-config.md) and keep only the canonical server templates inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but padded: the security-scan/cleanup instructions and concrete-Python-command handling are restated across the CRITICAL section, the Skill Acquisition Strategy, and Mode 1 Step 8, and the Language Resolution prose is verbose. It earns a 3 nowhere because repeated content competes with context.	2 / 3
Actionability	Concrete, executable guidance throughout — copy-paste bash commands, exit-code handling (Exit 0/1/2), exact payload JSON shapes, and full MCP server templates per runtime — matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation and feedback loops: the mode-dispatch tree, scan→BLOCKED→cleanup→warn flow, and the config-helper "STOP if unsafe structure" rule with explicit retry/verify checkpoints.	3 / 3
Progressive Disclosure	The overview points to real bundle files (references/update-config.mjs, references/config-template.yaml) and delegates detail to sibling skills (/aif-architecture, /aif-skill-generator) at roughly one level of depth, with well-signaled navigation.	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.

A concise, third-person description that states concrete capabilities and pairs them with an explicit, natural-language trigger clause. It cleanly answers both what the skill does and when to invoke it, with low conflict risk. No meaningful weaknesses to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers" — matching the multi-action anchor rather than the vague or partial ones.	3 / 3
Completeness	Both "what does this do" (the four actions) and "when should Claude use it" (an explicit "Use when..." clause) are clearly answered, satisfying the top anchor.	3 / 3
Trigger Term Quality	Natural trigger phrases a user would actually say are present: "starting new project, setting up AI context, or asking \"set up project\", \"configure AI\", \"what skills do I need\"", giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The project-setup / agent-context niche with explicit triggers like "set up project" and "configure AI" is clearly distinguishable from other skills and unlikely to conflict.	3 / 3
	Total	12 / 12 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 (783 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: 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.