CtrlK
BlogDocsLog inGet started
Tessl Logo

pua-en

Put your AI on a Performance Improvement Plan. Forces exhaustive problem-solving with Western big-tech performance culture rhetoric and structured debugging. Trigger when: (1) task failed 2+ times or stuck tweaking same approach; (2) about to say 'I cannot', suggest manual work, or blame environment without verifying; (3) being passive—not searching, not reading source, just waiting; (4) user frustration: 'try harder', 'stop giving up', 'figure it out', 'again???', or similar. Also for complex debugging, env issues, config/deployment failures. All task types: code, config, research, writing, deployment, infra, API. Do NOT trigger on first-attempt failures or when a known fix is executing.

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

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./codebuddy/pua-en/SKILL.md

The canonical home for this skill is pua-en in tanweai/pua

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced behavioral skill with concrete templates and a clear core methodology. Its weakness is size and redundancy — a monolithic file with overlapping frameworks and inline rhetorical content that would benefit from splitting into reference files.

Suggestions

Split the Corporate PIP Flavor Pack and/or the Anti-Rationalization Table into a reference file (e.g. references/flavors.md) and link to it from SKILL.md to reduce the monolithic wall and improve progressive disclosure.

Consolidate the overlapping 5-step Universal Methodology and 7-Point Checklist (or explicitly state their relationship) to remove redundancy and tighten conciseness.

Either provide the referenced 'agents/pua-enforcer.md' bundle file or remove the dangling reference so navigation links resolve.

DimensionReasoningScore

Conciseness

The ~340-line body is mostly purposeful original rhetoric rather than concepts Claude already knows, but it carries real redundancy: the 7-Point Checklist overlaps the 5-step Universal Methodology, the Anti-Rationalization Table overlaps the Proactivity Enforcement Rhetoric, and the Flavor Pack is long prose that could be trimmed.

2 / 3

Actionability

Highly concrete and copy-pasteable for an instruction skill: ordered 5-step methodology with per-scenario sub-actions, a 7-item checklist, and exact output templates like '[Auto-select: X Flavor | Because: ...]' and the [PIP-REPORT] block.

3 / 3

Workflow Clarity

The Universal Methodology is a clearly sequenced 5-step flow with explicit ordering ('in order', 'skipping any one = PIP') and checkpoints ('Dimensions 1-4 must be completed before asking the user anything'), with the 7-point checklist and escalation levels cleanly scoped to specific trigger conditions.

3 / 3

Progressive Disclosure

Well-organized with clear headers, but everything lives in one monolithic ~340-line SKILL.md with no bundle files; the Flavor Pack, Anti-Rationalization Table, and detailed methodology are inline content that could be split into reference files, and 'agents/pua-enforcer.md' is referenced but absent from the bundle.

2 / 3

Total

10

/

12

Passed

Description

82%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, trigger-rich description that explicitly covers what, when, and when-not in natural user language. Its main weaknesses are a second-person opening phrase and broad 'all task types' framing that raises overlap risk with general debugging skills.

Suggestions

Rewrite the opening in third person (e.g. 'Forces exhaustive problem-solving...') to drop the 'your AI' second-person voice and recover the specificity point.

Tighten the broad 'Also for complex debugging, env issues, config/deployment failures. All task types: ...' scope so the description signals a clearer niche and lowers conflict with general debugging/ops skills.

Replace 'Western big-tech performance culture rhetoric' buzzword phrasing with a more concrete action verb to sharpen specificity.

DimensionReasoningScore

Specificity

Names several concrete mechanisms ('Forces exhaustive problem-solving', 'structured debugging', 'performance culture rhetoric') plus an enumerated task-type list, matching the multiple-specific-actions anchor; reduced one level for the second-person imperative 'Put your AI on a Performance Improvement Plan' per the voice penalty.

2 / 3

Completeness

Clearly answers both what ('Forces exhaustive problem-solving...') and when via an explicit numbered 'Trigger when:' list, plus a negative-trigger clause ('Do NOT trigger on first-attempt failures...').

3 / 3

Trigger Term Quality

Embeds natural user phrases users would actually say — 'try harder', 'stop giving up', 'figure it out', 'again???', 'I cannot' — giving strong coverage of real trigger language rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The behavioral triggers (giving up, passive waiting) are distinctive, but 'Also for complex debugging, env issues, config/deployment failures' and 'All task types: code, config, research, writing, deployment, infra, API' broaden it enough to overlap with general debugging/ops skills.

2 / 3

Total

10

/

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.