CtrlK
BlogDocsLog inGet started
Tessl Logo

pua-teardown-all

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

57

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

72%

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

The body is lean and appropriately organized for a simple instruction-only skill, but it stops short of giving concrete commands and omits a validation checkpoint for its destructive file operations. Adding a sequenced teardown step list with a verification check would raise workflow clarity and actionability.

Suggestions

Add a brief sequenced step list (e.g., 1. list active PUA/loop state, 2. confirm destructive cleanup with the user, 3. delete files, 4. verify config) to make the workflow explicit.

Include a concrete verification command or check (e.g., confirm files removed / config intact) before claiming completion, since this is a destructive operation.

Provide at least one concrete executable command for the teardown or config update to lift actionability from instruction-only to copy-paste ready.

DimensionReasoningScore

Conciseness

Lean, instruction-only body with no padding or explanation of concepts Claude already knows; every sentence carries actionable guidance.

3 / 3

Actionability

Guidance is specific ('preserve unknown fields', 'create ~/.pua/ if missing', 'do not claim completion without evidence') but provides no concrete executable commands or code for an instruction-only skill.

2 / 3

Workflow Clarity

The destructive file-deletion operation lacks an explicit validation/feedback-loop checkpoint, and steps are imperative sentences rather than a sequenced workflow with verification — capping at 2 per the rubric.

2 / 3

Progressive Disclosure

A short, well-organized single-section body with no need for external references; appropriate for a simple under-50-line skill.

3 / 3

Total

10

/

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 conveys a clear, distinct niche with usable trigger tokens, but it omits an explicit 'Use when' clause and only names a single action, leaving the 'when' and breadth of capability implicit. Adding a trigger clause and one or two more concrete actions would round it out.

Suggestions

Add an explicit 'Use when ...' clause stating when Claude should invoke this alias (e.g., 'Use when tearing down or resetting all PUA agent and loop state').

Name the concrete teardown actions performed (e.g., 'release agent state, clear loop state, and remove session files') rather than only 'teardown alias'.

Trim the self-referential phrasing ('Codex subcommand mapping for Claude Code /pua:teardown-all style usage') to tighten the description.

DimensionReasoningScore

Specificity

Names a concrete action ('teardown alias') and the Codex/Claude Code mapping, but lists only a single action rather than multiple specific capabilities.

2 / 3

Completeness

States what the alias does but lacks an explicit 'Use when...' trigger clause, so the 'when' is only implied — capping completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

Includes concrete trigger tokens a user would actually type ('/pua:teardown-all', '$pua-teardown-all'), though coverage of natural-language variations is limited.

2 / 3

Distinctiveness Conflict Risk

Niche-specific tokens ('PUA', '/pua:teardown-all', '$pua-teardown-all') give it a clear, distinct identity unlikely to fire for unrelated skills.

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.