uinaf/agent-readiness
Audit and build the infrastructure a repo needs so agents can work autonomously — boot scripts, smoke tests, CI/CD gates, dev environment setup, observability, and isolation. Use when a repo can't boot, tests are broken or missing, there's no dev environment, agents can't verify their work, or agents need human help to get anything done. Do not use for reviewing an existing diff or for documentation-only cleanup.
97
100%
Does it follow best practices?
Impact
87%
1.03xAverage 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 clearly defines its scope (infrastructure for agent autonomy), lists specific concrete deliverables, provides explicit trigger conditions via a 'Use when' clause, and even includes negative boundaries with a 'Do not use' clause. It uses proper third-person voice throughout and covers natural terms users would employ when facing these problems.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: boot scripts, smoke tests, CI/CD gates, dev environment setup, observability, and isolation. These are clearly defined infrastructure components. | 3 / 3 |
Completeness | Clearly answers 'what' (audit and build infrastructure — boot scripts, smoke tests, CI/CD gates, etc.) and 'when' (explicit 'Use when' clause with multiple trigger scenarios). Also includes a 'Do not use' clause which further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'repo can't boot', 'tests are broken or missing', 'no dev environment', 'agents can't verify their work', 'CI/CD', 'smoke tests'. These cover common pain points users would describe naturally. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around agent-readiness infrastructure for repos. The 'Do not use' clause for diff review and documentation cleanup explicitly reduces conflict with code review or documentation skills. The focus on agent autonomy infrastructure is highly distinctive. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exceptionally well-structured skill that balances conciseness with actionability. The 7-layer stack provides a clear mental model, the workflow has explicit sequencing and validation checkpoints, and references are appropriately externalized. The anti-patterns section adds value by preventing common failure modes without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It assumes Claude's competence, avoids explaining basic concepts, and uses terse but clear language. The principles, anti-patterns, and workflow steps all earn their place without padding. | 3 / 3 |
Actionability | Provides concrete, executable bash scripts for boot and smoke steps, specific commands (curl, jq, playwright), a clear grading output format, and actionable patterns. The enforce hook example is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 4-step workflow (Audit → Setup → Improve → Hand Off) is clearly sequenced with explicit ordering within Setup (Boot → Smoke → Interact → E2e → Enforce → Observe → Isolate). The audit step includes validation criteria with pass/partial/fail statuses, and the hand-off step provides clear exit conditions (C+ grade). The boot script includes a health-check feedback loop with timeout and error handling. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure: core workflow is inline with concise examples, while detailed patterns are delegated to clearly signaled one-level-deep references (grading.md, setup-patterns.md, industry-examples.md). Handoffs to other skills (review, verify, docs) are clearly defined at the top. | 3 / 3 |
Total | 12 / 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