pua-mama

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

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

67%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 commendably lean and includes a clear verification red line plus config safeguards, but its guidance is largely abstract directives with no concrete commands or steps for loading the protocol and switching narration style. Actionability is the primary weakness.

Suggestions

Replace 'Load and follow the mama skill/protocol' with a concrete command or step showing how to load it and switch narration style, so guidance is executable.

Add a brief numbered workflow (load mama protocol -> switch narration style -> apply config safeguards -> verify with command/output evidence) to make the sequence explicit.

Specify how to 'preserve unknown fields' in ~/.pua/config.json (e.g., a read-modify-write pattern or jq command) rather than stating the requirement abstractly.

Dimension	Reasoning	Score
Conciseness	A lean four-paragraph body that assumes Claude knows the mama skill/protocol and adds no padding or concept explanations; every token earns its place. Not 4 because there is no over-explanation left to trim.	5 / 5
Actionability	Gives high-level directives ('Load and follow the mama skill/protocol', 'switching the visible narration style to Chinese-mom nagging mode') but no concrete command, code, or specific steps to execute the load or style switch. Not 3 because guidance is hints rather than concrete steps; not 1 because some directives like config preservation are semi-concrete.	2 / 5
Workflow Clarity	Directives form a clear single-purpose flow with an explicit verification red line ('Do not claim completion without command/output evidence') and config-change safeguards, though steps are not formally numbered. Not 5 because there is no formal sequence or feedback loop; not 3 because the validation checkpoint is explicit rather than missing.	4 / 5
Progressive Disclosure	Short, logically grouped body well under 50 lines with no need for external references, but it lacks section headers beyond the H1 title, leaving minor organization gaps. Not 5 because there are no well-signaled section structures; not 3 because content is appropriately compact rather than inlined bulk.	4 / 5
	Total	15 / 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 carves out a distinct, low-conflict niche and names a couple of concrete actions, but it omits explicit 'Use when...' trigger guidance and leans on command-syntax jargon over natural user phrases. Completeness and trigger-term quality are the main weaknesses.

Suggestions

Add an explicit 'Use when...' clause naming the situations that trigger this alias (e.g., 'Use when the user invokes $pua-mama or asks for Chinese-mom nagging mode') to raise completeness and trigger-term quality.

Expand specificity by listing the concrete actions the alias performs beyond 'mapping' and 'invoke' (e.g., what the mama protocol does, what the narration switch changes).

Include natural-language synonyms users might say ('nagging mode', 'Chinese mom style') alongside the command-syntax tokens so triggers match real phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain ('Codex alias', 'subcommand mapping') with a couple of concrete actions ('subcommand mapping', 'invoke with $pua-mama'), but coverage is limited to 1-2 actions rather than comprehensive. Not 2 because it does name actions beyond the domain; not 4 because it lists only a couple of actions with gaps.	3 / 5
Completeness	States clearly what it is ('PUA mama alias for Codex', 'Codex subcommand mapping') and how to invoke, but provides no 'Use when...' trigger guidance for when to use it, capping completeness at 3 per the rubric guideline. Not 4 because 'when' is entirely missing; not 2 because the 'what' is clear.	3 / 5
Trigger Term Quality	Includes skill-specific tokens ('PUA mama', '/pua:mama', '$pua-mama') but these are command-syntax jargon rather than natural user phrases, and synonyms/variations are missing. Not 4 because natural phrase variations are absent; not 2 because there is more than generic keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The 'pua-mama'/'$pua-mama' niche is highly specific with unique triggers, creating minimal conflict risk with other skills. Not 4 because it is clearly distinct with its own command tokens rather than merely mostly distinct.	5 / 5
	Total	14 / 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-mama/SKILL.md
Commit: ac50267

Reviewed: ~10 hours 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.