CtrlK
BlogDocsLog inGet started
Tessl Logo

pua-p7

PUA P7 alias for Codex. Codex subcommand mapping for Claude Code /pua:p7 style usage; invoke with $pua-p7.

61

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./codex/pua-p7/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The content is concise, well-organized, and presents a clear workflow with an explicit verification gate, fitting a simple single-purpose skill. Its main weakness is actionability, since core protocol detail is deferred to an external 'p7 skill/protocol' that is neither bundled nor referenced by path.

Suggestions

Add a concrete pointer to the p7 skill/protocol (a file path or reference) or inline its three self-review questions so the body is self-contained and fully actionable.

Specify what 'self-review with three questions' means by listing the three questions, rather than leaving them undefined.

Optionally include a minimal example of the expected [P7-COMPLETION] deliverable format so the output is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean with no concept padding; every line is operational ('plan, implement, self-review', config handling rules) and assumes Claude's competence, matching the 'lean and efficient' anchor.

3 / 3

Actionability

It gives concrete behavioral rules (preserve unknown fields, create ~/.pua/ if missing, require command/output evidence) but defers core detail to 'the p7 skill/protocol' without a path or bundled reference, leaving key details incomplete.

2 / 3

Workflow Clarity

For a simple skill it lays out a clear sequence (plan -> implement -> self-review -> deliver [P7-COMPLETION]) with an explicit validation checkpoint ('Do not claim completion without command/output evidence') and guards on config changes.

3 / 3

Progressive Disclosure

It is a short, well-organized skill under 50 lines with no need for bundled references; per the simple-skills note, clean organization alone merits a 3 even without external file references.

3 / 3

Total

11

/

12

Passed

Description

57%

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 clearly identifies a distinct command alias niche but relies on technical invocation syntax rather than natural trigger phrases and omits an explicit 'Use when' clause. Specificity and completeness are adequate but not comprehensive.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this alias (e.g., when the user requests the P7 protocol or asks to act as a P7 senior engineer).

Expand specificity by listing the concrete actions the alias performs (e.g., 'Plans, implements, and self-reviews work using the P7 protocol, then delivers a [P7-COMPLETION]') rather than describing it only as a mapping.

Include natural-language trigger terms (e.g., 'P7', 'senior engineer review', 'self-review protocol') alongside the command syntax so users can discover it via conversational phrasing.

DimensionReasoningScore

Specificity

It names a concrete domain ("Codex subcommand mapping", "alias") but does not enumerate multiple specific actions, so it sits at 'names domain and some actions' rather than the multi-action level 3.

2 / 3

Completeness

It states what the skill is but lacks an explicit 'Use when...' clause; the when-to-use guidance is only implied by 'invoke with $pua-p7', which caps completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

It includes the actual command tokens a user would invoke ("/pua:p7", "$pua-p7"), which are the relevant keywords for this niche, but offers no natural-language variations, keeping it below the good-coverage level 3.

2 / 3

Distinctiveness Conflict Risk

The highly specific named command identifiers ('/pua:p7', '$pua-p7') give it a clear niche that is unlikely to trigger for the wrong skill.

3 / 3

Total

9

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tanweai/pua
Reviewed

Table of Contents

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.