CtrlK
BlogDocsLog inGet started
Tessl Logo

pua-trae

Trae-optimized PUA high-agency governance skill for npx skills installs. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or unverified completion. Do not trigger for normal first-attempt tasks.

67

Quality

80%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a tight, well-structured instruction-only governance contract with concrete templates, an explicit validation checkpoint, and a destructive-operation confirmation gate. The main room for improvement is tightening the cultural-narrative section and making the validate-fix retry loop fully explicit.

Suggestions

Trim the six-brand cultural-narrative list to the 2-3 most useful bindings, or move the full list to a reference file to reduce tokens.

Make the validate->fix->retry feedback loop explicit in the confidence loop (e.g., 'on failure: fix root cause and re-run step 3 before switching paths') to strengthen workflow_clarity.

Add one or two concrete command examples for the verification step (e.g., a sample lint/build/curl invocation) to lift actionability toward fully executable.

DimensionReasoningScore

Conciseness

The body is mostly efficient with terse templates and tables, assuming Claude's familiarity with the cultural references; minor rhetorical asides ('INTJ 版理解') and the six-brand narrative list add light padding that could be trimmed.

4 / 5

Actionability

Concrete executable artifacts are present (the [PUA-DIAGNOSIS] template, the 6-step loop naming specific verification types, and the structured delivery template); as an instruction-only skill this is actionable guidance with only minor gaps in concrete command examples.

4 / 5

Workflow Clarity

The 100%-confidence loop is clearly sequenced with a validation checkpoint (step 3), a two-failure branch (step 4), and an explicit confirmation gate before destructive/batch environment changes; the validate->fix retry loop is implied rather than fully spelled out.

4 / 5

Progressive Disclosure

Content is self-contained in a single well-organized SKILL.md with clear section headers and no nested references; under the simple/self-contained skill exception this clean one-level structure earns a top score.

5 / 5

Total

17

/

20

Passed

Description

82%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 is strong: it explicitly covers both what and when with concrete, natural trigger phrases and a clear, low-conflict niche. Its main weakness is an abstract capability verb ('governance') rather than enumerated concrete actions.

DimensionReasoningScore

Specificity

It names the niche ('PUA high-agency governance skill for npx skills installs') and lists several concrete trigger conditions, but the core capability ('governance') is abstract and doesn't enumerate concrete actions the skill performs, keeping it below the 'several specific actions' anchor.

3 / 5

Completeness

It explicitly answers both 'what' ('PUA high-agency governance skill for npx skills installs') and 'when' with concrete trigger phrases ('Use only for explicit PUA requests, repeated failures... Do not trigger for normal first-attempt tasks'), matching the explicit-both anchor.

5 / 5

Trigger Term Quality

Natural user phrasings are well covered ('explicit PUA requests', 'try harder', '换个方法', 'repeated failures', 'user frustration', 'giving-up/passive behavior'), with only a few common synonyms missing.

4 / 5

Distinctiveness Conflict Risk

The PUA/high-agency-governance niche is distinctive and the explicit anti-trigger ('Do not trigger for normal first-attempt tasks') minimizes conflict with ordinary skills.

5 / 5

Total

17

/

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.

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.