pua-loop

PUA Loop — guided iterative development with recurring checks, completion evidence, and pause/abort markers. Use only when the user explicitly asks for loop/自动迭代 mode.

Quality

71%

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 ./skills/pua-loop/SKILL.md

Quality

Content

81%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 tightly structured, actionable iterative-loop protocol with strong workflow clarity and explicit validation feedback loops; its main weaknesses are a dangling script reference and minor backstory verbosity.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational (gate protocol, core rules, startup, escalation table, completion checklist) and avoids explaining concepts Claude already knows; the only trim candidates are the autoresearch backstory epigraph and comparison table, which are minor.	4 / 5
Actionability	Provides a concrete executable startup command, explicit --verify inference rules with examples, a JSONL history schema, and concrete markers (<promise>, <loop-abort>, <loop-pause>); the referenced setup script is not present in the bundle, a minor gap.	4 / 5
Workflow Clarity	The iterative workflow is fully sequenced (read history → git log → execute → verify → repeat) with explicit two-phase validation (Phase 1 self-verify, Phase 2 Oracle), a rejection-recovery feedback loop, and stall-detection checkpoints.	5 / 5
Progressive Disclosure	Well-organized into clear labeled sections as a self-contained single-file protocol, but it exceeds 50 lines and references a scripts/setup-pua-loop.sh file that is not in the bundle, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

62%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 clearly defines a niche (gated iterative loop) and includes an explicit trigger clause, but its capability list is conceptual rather than concrete and its trigger vocabulary is narrow.

Suggestions

Replace abstract feature terms ("completion evidence", "pause/abort markers") with concrete verbs, e.g. "runs a verify command each iteration, emits pause/abort markers, appends results to a history log".

Broaden trigger terms to include natural synonyms like "iterate", "auto-iterate", and "loop mode" so users phrasing it differently still match.

Tighten the "what" into a compact action list so both what and when read as concrete and comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain ("guided iterative development") and several features ("recurring checks, completion evidence, and pause/abort markers"), but the actions are conceptual mechanisms rather than concrete capabilities, so it does not reach comprehensive coverage.	3 / 5
Completeness	States both a clear "what" and an explicit "when" ("Use only when the user explicitly asks for loop/自动迭代 mode"), but the "what" is somewhat abstract rather than listing concrete actions, keeping it just below a 5.	4 / 5
Trigger Term Quality	Includes the natural term "loop" and "自动迭代 mode", but coverage is narrow and missing common variations/synonyms like "iterate", "auto-iterate", or "loop mode".	3 / 5
Distinctiveness Conflict Risk	The distinct "PUA Loop" name plus a gated trigger ("Use only when the user explicitly asks...") make it mostly distinct with only minor overlap risk against generic loop skills.	4 / 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: skills/pua-loop/SKILL.md
Commit: ac50267

Reviewed: 10 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.