to-spec

把当前对话转成 spec 并发布到项目 issue tracker——不做访谈，只综合已经讨论的内容。

Quality

61%

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/engineering/to-spec/SKILL.md

Quality

Content

72%

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 lean, actionable instruction skill centered on a concrete spec template, with a clear sequenced process and one user-confirmation checkpoint. Its main gaps are a missing verification step before publishing and minor conciseness slack in the seams guidance.

Suggestions

Add an explicit validation/confirmation checkpoint before publishing to the issue tracker (e.g. review the drafted spec against the template and confirm scope with the user) to strengthen the workflow's feedback loop for the outward publish action.

Consolidate the seams guidance (steps about preferring existing seams, highest-level seams, and 'fewer is better') into a single tighter paragraph to improve token efficiency.

Clarify what to do if the issue tracker or triage label vocabulary is genuinely unavailable beyond pointing to /setup-matt-pocock-skills, so the publish step is not blocked ambiguously.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude already knows, but the seams guidance is spread across multiple lines and could be tightened. It is not a 3 because of minor redundancy in the seams discussion, and not a 1 because there is no padded conceptual exposition.	2 / 3
Actionability	It provides a concrete, copy-paste spec template with explicit section structure, a specific user-story format plus a worked example, and a concrete triage label ('ready-for-agent'). It is not a 2 because the guidance is specific and complete rather than abstract or pseudocode-level.	3 / 3
Workflow Clarity	The three-step Process is clearly sequenced and includes one explicit checkpoint ('与用户确认这些 seams 是否符合预期'), but there is no verification step before the outward publish-to-issue-tracker action. It is not a 3 because the publish step lacks an explicit validation/feedback checkpoint, and not a 1 because the sequence and one checkpoint are present.	2 / 3
Progressive Disclosure	The skill is self-contained with well-organized sections (Process, spec-template) and no nested or multi-level external references; the inline template is the core deliverable and is appropriately kept inline. It is not a 2 because there is no monolithic wall of misplaced reference content, and the structure is clear and navigable.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 states a clear, concrete purpose but omits any explicit usage trigger and only partially covers natural keyword variations. Adding a 'Use when…' clause and common synonyms (PRD, 需求文档) would raise completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to turn a conversation/discussion into a spec (PRD) and publish it as an issue.'

Broaden trigger terms to include natural variations users might say: PRD, 需求文档, 整理讨论, 发 issue, 提交需求.

State the capability in third-person declarative form and confirm it is distinguishable from general documentation/writing skills by naming the issue-tracker publication step as the distinguishing action.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ('把当前对话转成 spec' and '发布到项目 issue tracker'), but does not comprehensively enumerate the skill's capabilities. It is not a 3 because only two actions are listed rather than multiple specific ones, and not a 1 because the actions are concrete rather than abstract.	2 / 3
Completeness	It clearly states what the skill does, but provides no explicit 'Use when…' trigger guidance, so per the rubric completeness is capped at 2. It is not a 1 because the 'what' is clearly present, and not a 3 because the 'when' is entirely absent rather than explicit.	2 / 3
Trigger Term Quality	It includes some relevant terms a user might say ('spec', 'issue tracker', '对话'), but misses common natural variations such as 'PRD', '需求文档', or '整理讨论'. It is not a 3 because coverage of natural trigger phrasings is incomplete, and not a 1 because the terms present are user-natural rather than pure jargon.	2 / 3
Distinctiveness Conflict Risk	The spec-from-conversation-plus-issue-tracker niche is fairly specific, but the lack of explicit trigger terms means it could still overlap with related writing/documentation skills. It is not a 3 because distinct triggers are missing, and not a 1 because the niche is not generic.	2 / 3
	Total	8 / 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: vinvcn/mattpocock-skills-zh-CN
Path: skills/engineering/to-spec/SKILL.md
Commit: f2b2464

Reviewed: 1 day 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.