shot

PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.

Quality

37%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/shot/SKILL.md

Quality

Content

40%

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

The body has strong workflow sequencing and several concrete templates, but it is padded with redundant persona rhetoric and critically depends on reference files that are absent from the bundle. As shipped, large sections ('详见 references/...') resolve to nothing.

Suggestions

Ship the missing bundle files (references/p7-p9-p10-protocol.md, flavors.md, platform.md, agents/*.md) so the signaled progressive-disclosure paths actually resolve.

Collapse the four overlapping retaliation systems (压力升级 table, 抗合理化表, 味道选择器, 味道包) into one canonical section and move the 14-flavor templates into references/flavors.md to cut ~100+ lines of redundancy.

Move inline persona content (e.g. the full 味道包) out of SKILL.md so the body becomes a lean overview pointing one level deep, matching the progressive-disclosure anchor.

Dimension	Reasoning	Score
Conciseness	The ~450-line body is padded with four overlapping retaliation systems (压力升级, 抗合理化表, 味道选择器, and a 14-flavor 味道包) that repeat the same rhetoric, far beyond 'could be tightened'.	1 / 3
Actionability	Concrete copy-paste templates exist (P8→P7 WHAT/WHERE/DONE/DON'T, [PUA-REPORT], 7-item checklist, 5-step method), but key executable detail is delegated to '详见 references/...' files that do not exist, leaving it incomplete.	2 / 3
Workflow Clarity	The 5-step methodology, L1–L4 escalation with强制动作, P8-manages-P7 decision tree, and numbered collaboration rules are clearly sequenced with explicit verification checkpoints (build/curl/测试) and checklists.	3 / 3
Progressive Disclosure	References are one-level and signaled, but none of the referenced files (references/p7\|p9\|p10-protocol.md, flavors.md, platform.md, agents/*.md) exist, so critical detail is unresolvable; the body is also a monolithic wall.	1 / 3
	Total	7 / 12 Passed

Description

35%

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 signals a niche variant but leans on brand jargon and abstract phrasing rather than concrete capabilities or natural user triggers. It lacks an explicit 'Use when...' clause, so it answers 'what' only weakly and leaves 'when' implied.

Suggestions

Add a concrete capability list (e.g. 'injects PUA behavior protocols into sub-agents, emits [PUA生效] markers, switches company-flavor retaliation on failure') instead of abstract phrases like 'evidence-first behavior'.

Append an explicit trigger clause: 'Use when spawning sub-agents that need PUA proactiveness/verification flavor, or for short sessions where the full PUA skill is too large.'

Replace brand-only terms with natural language a user would actually say (e.g. 'proactive agent behavior', 'verification-before-completion coaching') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Names a domain and an action ('compact all-in-one PUA reference for explicit injection into sub-agents') but offers no concrete capability list, and 'evidence-first behavior' is abstract.	2 / 3
Completeness	A weak 'what' and an implied 'when' ('for explicit injection into sub-agents or short sessions') are present, but there is no 'Use when...' trigger clause, capping completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'PUA', 'sub-agents', and 'short sessions' are internal/brand jargon a user would not naturally say when reaching for this skill.	1 / 3
Distinctiveness Conflict Risk	'PUA Shot' marks a niche variant, but the jargon-heavy phrasing reads as a sibling of other PUA skills and is not clearly distinct to an outside reader.	2 / 3
	Total	7 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 15 missing	Warning

	Total	15 / 16 Passed

Repository: tanweai/pua
Path: skills/shot/SKILL.md
Commit: 3fd4e5a

Reviewed: 2 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.