Name: pua-en
Rating: 64 (1 reviews)
Author: tanweai

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.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

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

Quality

Content

62%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.

A well-sequenced, highly actionable instruction skill with explicit validation checkpoints and feedback loops, undermined by heavy rhetorical padding and a monolithic single-file structure that should be split into reference files.

Suggestions

Move the Corporate PIP Flavor Pack and Anti-Rationalization Table into a references/ file (e.g. FLAVOR_PACKS.md) and summarize the flavor list in SKILL.md with one-line pointers, cutting the bulk of the verbose monologues from the main file.

Tighten redundant rhetoric: the Proactivity Enforcement Rhetoric, Anti-Rationalization Table, and flavor packs restate the same Ownership/Dive Deep/Bias for Action themes — consolidate to a single canonical list and drop the rest.

Since the file is well over 50 lines, split the Agent Team Integration section into its own reference (e.g. AGENT_TEAM.md) and keep only the trigger/escalation overview inline to improve navigation.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: eight multi-paragraph corporate flavor-pack monologues plus an Anti-Rationalization Table and Proactivity Enforcement Rhetoric that overlap conceptually, adding substantial tokens Claude does not strictly need.	2 / 5
Actionability	Provides concrete, executable instruction guidance — a sequenced 5-step methodology, a 7-point checklist, escalation-to-mandatory-action mapping, and copy-paste formats like the [PIP-REPORT] block and [Auto-select: ...] tag — with only minor abstraction gaps.	4 / 5
Workflow Clarity	Clear sequenced workflow (Pattern Recognition → Elevate → Self-Review → Execute → Retrospective) with explicit validation checkpoints, closed-loop/evidence enforcement, checklists, and a retrospective feedback loop for error recovery.	5 / 5
Progressive Disclosure	Good section headers and tables give it structure, but everything is inlined into one ~344-line SKILL.md with no references/ or assets/ — the flavor-pack catalog and anti-rationalization table clearly belong in separate reference files.	3 / 5
	Total	14 / 20 Passed

Description

87%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.

A strong, explicit description that clearly states what the skill does and when to trigger it, with rich natural-language trigger phrases. Its only real weakness is the over-broad 'all task types' scope, which raises conflict risk with adjacent debugging/verification skills.

Dimension	Reasoning	Score
Specificity	Names several concrete mechanisms — 'Forces exhaustive problem-solving', 'structured debugging', proactivity enforcement, and pressure escalation — though they are stated at a fairly high level rather than as fully concrete operations.	4 / 5
Completeness	Explicitly answers both 'what' (forces exhaustive problem-solving with big-tech rhetoric and structured debugging) and 'when' (four numbered triggers, an 'Also for...' clause, and an explicit 'Do NOT trigger on first-attempt failures' exclusion).	5 / 5
Trigger Term Quality	Includes natural user-frustration phrases verbatim ('try harder', 'stop giving up', 'figure it out', 'again???', 'I cannot') plus behavioral signals like 'stuck tweaking same approach', giving comprehensive trigger coverage.	5 / 5
Distinctiveness Conflict Risk	The passivity/repeated-failure niche is distinctive, but 'All task types: code, config, research, writing, deployment, infra, API' plus 'Also for complex debugging, env issues, config/deployment failures' is broad enough to overlap with systematic-debugging and verification skills.	3 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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-en/SKILL.md
Commit: ac50267

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.