CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pua-on

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

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

86%Weight 40%Scale 1-5

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

The body is concise, well-structured, and actionable with a clear sequence and an explicit completion-evidence checkpoint. Main gap is the absence of a copy-paste command for the config edit and a more specific validation step.

Suggestions

Provide a concrete, copy-paste-ready command for editing ~/.pua/config.json (e.g., a jq snippet) so the guidance is fully executable.

Add a specific validation step such as re-reading the config to confirm always_on=true rather than only the generic 'command/output evidence' instruction.

Clarify the report step with an example of the expected output evidence to attach when claiming completion.

DimensionReasoningScore

Conciseness

The body is a lean ~7 lines with no padding and no explanation of concepts Claude already knows; every line earns its place. Not below 5 because there is no unnecessary verbosity to trim.

5 / 5

Actionability

Gives concrete, specific guidance (path ~/.pua/config.json, field always_on=true, restore feedback_frequency to 5, report [PUA ON]) but provides no copy-paste-ready command for editing the JSON. Not a 5 because no executable command is given; not a 3 because the field-level instructions are concrete and actionable rather than pseudocode.

4 / 5

Workflow Clarity

A clear sequence (preserve config -> set always_on -> restore feedback_frequency if 0 -> report) with an explicit verification checkpoint ('Do not claim completion without command/output evidence'), so the destructive-config cap at 3 does not apply. Not a 5 because the verification is generic ('command/output evidence') rather than a specific validation of the written config; not a 3 because a real checkpoint is present.

4 / 5

Progressive Disclosure

Under 50 lines, no bundle files, and no need for external references; content is well-organized into a heading and logically ordered paragraphs (what it is, enable steps, constraints), meeting the simple-skill exception. Not below 5 because no further file structure is warranted for this scope.

5 / 5

Total

18

/

20

Passed

Description

57%Weight 40%Scale 1-5

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 specific, distinct command alias but relies on command syntax for triggers and omits an explicit 'Use when...' clause. It is adequately specific and distinctive but would benefit from natural-language trigger phrasing.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when the user wants to enable PUA always-on mode via Codex').

Include natural-language trigger phrases beyond command syntax, such as 'enable PUA', 'always-on mode', or 'turn PUA on'.

Slightly expand the concrete actions named so the capability coverage reads as more comprehensive.

DimensionReasoningScore

Specificity

Names the domain ('PUA on alias for Codex', 'Codex subcommand mapping') plus 1-2 concrete actions (mapping a subcommand, invoking with $pua-on), but coverage is not comprehensive. Not a 2 because it does name concrete actions beyond just the domain; not a 4 because it lists few specific actions.

3 / 5

Completeness

Has a clear 'what' (a Codex alias mapping the /pua:on subcommand) but lacks an explicit 'Use when...' clause; 'invoke with $pua-on' is invocation syntax, only weakly implying 'when'. Per guidelines a missing 'Use when...' clause caps completeness at 3. Not a 4 because the 'when' is not explicitly stated.

3 / 5

Trigger Term Quality

Covers several forms of the trigger command ('pua on', '/pua:on', '$pua-on', 'Codex') but these are command-syntax tokens rather than natural-language phrases, and no synonyms or common variations are offered. Not a 4 because natural-language terms a user would say are missing; not a 2 because multiple relevant trigger forms are present.

3 / 5

Distinctiveness Conflict Risk

Targets a uniquely named command ('pua-on' / '/pua:on') with a clear niche and distinct triggers, creating minimal conflict risk with other skills. Not a 4 because the trigger is unambiguous and highly specific rather than overlapping with related skills.

5 / 5

Total

14

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tanweai/pua

Path

codex/pua-on/SKILL.md

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.