p7

P7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8. Produces: implementation plan + code + 3-question self-review, delivered via [P7-COMPLETION].

Quality

82%

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

Quality

Content

65%

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

The body is appropriately lean as a router-style overview, but it leans almost entirely on a referenced protocol file (`../pua/references/p7-protocol.md`) and the `/pua` core skill, neither of which is bundled here, leaving the concrete workflow unexecutable from the skill alone.

Suggestions

Ship the referenced protocol as a bundled references/ file (or inline the essential steps) so the skill is self-contained — the current `../pua/references/p7-protocol.md` path resolves to nothing in this bundle.

Add at least the explicit validation/feedback checkpoint for the three-step sequence in the body rather than deferring it entirely to the external protocol.

Include a brief, concrete description of the three-question self-review so the key deliverable is actionable without loading the external file.

Dimension	Reasoning	Score
Conciseness	The body is only four lines with no padding and no explanation of concepts Claude already knows — "先设计方案 + 影响分析，再实施编码，完成后三问自审查" is lean and every token earns its place. Not a 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Gives a high-level sequence and a named file to load ("详细协议见 `../pua/references/p7-protocol.md`。加载后按协议执行"), but all concrete, executable detail is offloaded and the referenced file is absent, so key details are missing. Not a 3 because there is no copy-paste-ready or fully executable guidance in the body; not a 1 because a concrete sequence and a specific pointer are present.	2 / 3
Workflow Clarity	A three-step sequence is present ("先设计方案 + 影响分析，再实施编码，完成后三问自审查") with an implicit self-review checkpoint, but validation/feedback-loop detail lives only in the missing external protocol. Not a 3 because checkpoints are implicit rather than explicit; not a 1 because a clear sequence is stated.	2 / 3
Progressive Disclosure	Structure is conceptually right (thin overview pointing one level deep to `../pua/references/p7-protocol.md`), but scored against the actual bundle: no references/scripts/assets exist and the referenced file does not resolve, so navigation is broken. Not a 3 because the referenced path is a dead pointer; not a 1 because the body is a thin, well-signaled overview rather than a monolithic wall of text.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, well-formed description: it names concrete deliverables, gives explicit 'Use when' triggers in natural user terms, and occupies a clearly distinct niche. It uses third person and avoids fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — "implementation plan + code + 3-question self-review, delivered via [P7-COMPLETION]" alongside "solution-driven execution under P8 supervision", matching the anchor for several specific concrete actions. It is not below 3 because the actions are concrete and enumerated rather than vague; there is no higher anchor.	3 / 3
Completeness	Explicitly answers both what ("solution-driven execution... Produces: implementation plan + code + 3-question self-review") and when ("Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8") with an explicit 'Use when' clause. Not a 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	Provides natural trigger terms a user of this system would say — "'P7模式', '方案驱动'" plus the sub-task executor condition — giving good coverage of natural terms. Not a 2 because the triggers are explicit and varied rather than a single generic keyword.	3 / 3
Distinctiveness Conflict Risk	Highly niche triggers ('P7模式', '方案驱动', '[P7-COMPLETION]', P8 supervision) form a distinct niche unlikely to trigger the wrong skill. Not a 2 because these terms are specific to this P7/P8 system and unlikely to overlap with unrelated skills.	3 / 3
	Total	12 / 12 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/p7/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.