CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

94

1.10x
Quality

94%

Does it follow best practices?

Impact

97%

1.10x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Content

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 well-structured, concise skill that defines a clear framework for making repos agent-ready. Its greatest strengths are the crisp workflow sequencing, compact output format, and appropriate use of progressive disclosure to reference files. The main weakness is that actionable implementation details are deferred to bundle files that weren't provided, meaning the SKILL.md alone gives directional guidance rather than fully executable patterns.

Suggestions

Consider adding one minimal but complete executable example inline (e.g., a full verify.sh script skeleton) so the skill is actionable even without the referenced setup-patterns.md file.

DimensionReasoningScore

Conciseness

The content is lean and well-structured. It avoids explaining concepts Claude already knows (no explanations of what CI/CD is, what Docker does, etc.), uses terse bullet formats, and every section earns its place. The 7-layer stack is presented as a compact reference table rather than verbose prose.

3 / 3

Actionability

The skill provides concrete examples (curl commands, pnpm dev, etc.) and a clear grading framework, but most guidance is directional rather than executable. There are no complete, copy-paste-ready scripts for boot/smoke/verify setup — the actual implementation patterns are deferred to referenced files (references/setup-patterns.md) which are not provided in the bundle.

2 / 3

Workflow Clarity

The 4-phase workflow (Audit → Setup → Improve → Stop) is clearly sequenced with explicit ordering within Setup (Boot → Smoke → Interact → E2e → Enforce → Observe → Isolate). The stop condition is well-defined (C+ grade), there's a validation checkpoint (grading before and after), and the output format provides a structured feedback loop with before/after grades and remaining gaps.

3 / 3

Progressive Disclosure

The skill is a well-organized overview that appropriately defers detailed content to one-level-deep references (references/grading.md, references/setup-patterns.md, references/industry-examples.md). References are clearly signaled with descriptive labels. The main document stays at the right level of abstraction without inlining content that belongs in reference files.

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.

This is an excellent skill description that clearly articulates specific capabilities (boot scripts, smoke tests, CI/CD gates, dev environment setup, observability, isolation), provides explicit trigger conditions tied to real failure scenarios, and includes negative boundaries to prevent misuse. It uses proper third-person voice and is concise yet comprehensive.

DimensionReasoningScore

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 rather than vague abstractions.

3 / 3

Completeness

Clearly answers 'what' (audit and build infrastructure — boot scripts, smoke tests, CI/CD gates, etc.) and 'when' (repo can't boot, tests broken/missing, no dev environment, agents can't verify work). Also includes a 'do not use' clause which further clarifies scope.

3 / 3

Trigger Term Quality

Includes natural terms users and agents would encounter: 'repo can't boot', 'tests are broken or missing', 'no dev environment', 'agents can't verify their work', 'CI/CD gates', 'smoke tests'. These map well to real scenarios a user would describe.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche around agent-readiness infrastructure for repos. The explicit 'do not use' clause for diff review and documentation cleanup further reduces conflict risk with code review or documentation skills. The focus on agent autonomy infrastructure is distinctive.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents