oh-my-ai/agent-init
Creates, updates, or prunes an AGENTS.md for any repository by auditing the codebase, detecting non-discoverable gaps, and drafting minimal high-signal instructions that agents cannot infer from reading the code.
90
94%
Does it follow best practices?
Impact
78%
1.06xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific concrete actions, comprehensive trigger terms, clear what/when guidance, and explicit negative boundaries to prevent conflicts. The inclusion of tools used and output location adds further clarity without unnecessary verbosity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creates, updates, or prunes an AGENTS.md', 'auditing the codebase', 'detecting non-discoverable gaps', 'drafting minimal high-signal instructions'. Also specifies outputs and tools used. | 3 / 3 |
Completeness | Clearly answers 'what' (creates/updates/prunes AGENTS.md by auditing codebase and detecting gaps) and 'when' (explicit triggers list). Also includes negative boundaries ('Do NOT use for') which further clarifies scope. | 3 / 3 |
Trigger Term Quality | Includes a comprehensive explicit list of natural trigger terms: 'AGENTS.md, agent setup, agent config, init agents, workspace setup, agent instructions, Claude setup'. These cover common variations a user would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche focused specifically on AGENTS.md files. The explicit 'Do NOT use for' clause (README, docs, CI, code editing) actively prevents conflicts with adjacent skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, well-structured skill that provides clear, actionable guidance for generating AGENTS.md files. Its greatest strengths are the explicit multi-phase workflow with validation checkpoints, the concrete worked example, and the strong discoverability filter concept. The main weakness is moderate verbosity — some concepts (especially around what to exclude) are restated across non-negotiables, process phases, the example, and anti-patterns, which could be tightened without losing clarity.
Suggestions
Consolidate the repeated messaging about discoverability filtering — the concept is stated in non-negotiables #2, #3, Phase 4 quality gate, the example's 'What is NOT included' note, and anti-patterns. Consider stating it once definitively and referencing that single statement elsewhere.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-written and mostly efficient, but it's quite long (~200+ lines) with some repetition. The non-negotiables, process phases, and anti-patterns sections overlap in messaging (e.g., the discoverability filter is restated multiple times). The example section includes a disclaimer about tech stack details that itself is somewhat verbose. However, most content earns its place given the complexity of the task. | 2 / 3 |
Actionability | Highly actionable throughout: provides exact heading structure for output, specific file paths to scan in a prioritized table, concrete gap classification categories with examples, specific good/bad question examples for Phase 3, a complete worked example showing input through output, and explicit quality gate criteria. The process is copy-paste executable. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow (Audit → Gap Detection → Clarification → Draft/Quality Gate/Approval) with clear sequencing, explicit validation checkpoints (quality gate in Phase 4, diff summary for updates), conditional logic (skip Phase 3 if no ambiguities), and a feedback loop (user approval with 'Needs changes' option). The requirement to log omissions in audit-notes.md adds traceability. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections and appropriate references to external files (audit-checklist.md, discoverability-filter.md) that are one level deep and clearly signaled. The main skill file serves as a comprehensive overview while deferring detailed procedures to supporting files. Content is logically organized from non-negotiables → output format → process phases → example → anti-patterns. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents