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.

84

1.00x
Quality

84%

Does it follow best practices?

Impact

88%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is actionable and well-organized with a clear workflow and concrete commands, but it is held back by a triple-stated stack, implicit per-step validation, and—most importantly—references to bundle files that are not present.

Suggestions

Create the missing bundle files (references/grading.md, references/setup-patterns.md, references/industry-examples.md) so the one-level-deep references resolve; otherwise inline the essential content from them.

Add an explicit per-layer validation checkpoint in the Setup workflow, e.g. "after adding each layer, re-run the audit and confirm that dimension moved toward pass before proceeding."

State the 7-layer stack once and reference it by name in the Concrete examples and Setup sections, and condense the Output formatting meta-rules into a shorter checklist.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining concepts Claude already knows, but the 7-layer stack is restated three times (definition, concrete examples, and the Setup order) and the Output formatting meta-rules run to seven sub-bullets that could be tightened.

2 / 3

Actionability

It provides concrete, copy-paste-ready commands ("curl http://127.0.0.1:3000/health", "make verify", "./scripts/verify.sh") and a directly reusable audit-output template, which is fully actionable for an instruction-oriented meta-skill.

3 / 3

Workflow Clarity

The Audit → Setup → Improve → Stop sequence is clearly ordered with a terminal grade gate, but intermediate validation checkpoints (e.g., re-running the audit after each layer) are implicit rather than explicit mechanical steps.

2 / 3

Progressive Disclosure

The body is well-structured with clearly signaled one-level-deep references, but the referenced bundle files (references/grading.md, references/setup-patterns.md, references/industry-examples.md) do not exist, so the disclosure leads to dead ends rather than available detail.

2 / 3

Total

9

/

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.

The description is specific, trigger-rich, and complete, with explicit what/when guidance and a conflict-reducing exclusion clause. It is a strong, well-scoped skill description.

DimensionReasoningScore

Specificity

It lists multiple concrete infrastructure actions — "boot scripts, smoke tests, CI/CD gates, dev environment setup, observability, and isolation" — matching the anchor for several specific concrete actions rather than vague domain references.

3 / 3

Completeness

It explicitly answers both what ("Audit and build the infrastructure…") and when via an explicit "Use when…" trigger clause, satisfying the top anchor for both.

3 / 3

Trigger Term Quality

The "Use when…" clause surfaces natural utterances a user would actually say ("a repo can't boot", "tests are broken or missing", "agents can't verify their work", "agents need human help"), giving good scenario coverage rather than jargon.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche (agent-readiness infrastructure) and adds a negative trigger ("Do not use for reviewing an existing diff or for documentation-only cleanup") that actively prevents overlap with review/docs skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

referenced_paths_exist

Referenced path issues: 10 missing

Warning

Total

14

/

16

Passed

Reviewed

Table of Contents