writing-shape

Writing, exploit：把原始素材塑造成文章，一段一段地推进。

Quality

75%

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/in-progress/writing-shape/SKILL.md

Quality

Content

100%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 an exemplary instruction-only skill: a clear six-step conversational loop with explicit user-agreement checkpoints, concrete decision rules for every format choice, literal dialogue moves, and a safe append-to-file protocol. It is token-efficient, self-contained, and fully actionable without any code or external references, which is appropriate for this skill type.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense: it explains only skill-specific concepts ("grounded", "pile", "exploit") and never background knowledge Claude already has. Every section — the loop, grounding, conversational moves, format arguments — carries unique instruction with no padding, matching the score-5 anchor ("every token earns its place"). It is not score 4 because there are no trimmable over-explanations anywhere.	5 / 5
Actionability	Guidance is fully executable for a conversational skill: literal questioning moves ("If I cut this, what breaks?"), concrete decision rules ("如果同一形状以相同 fields 重复 3 次以上，用 table", `> [!TIP]` callout syntax, block vs. inline code criteria), and a precise write protocol ("每次写入前都从磁盘重新读取文件… 永远不要盲目 overwrite"). Score 5 rather than 4 because the specific examples cover the common cases with no gaps.	5 / 5
Workflow Clarity	The six-step loop is clearly sequenced with explicit checkpoints: user sign-off per block ("迫使用户选择", "达成一致"), a maintained checklist of grounded concepts ("维护一份到目前为止已 grounded 内容的清单"), drift-recovery feedback ("Either re-thread it or change the opening"), and gap escalation ("give me one now or we cut this section"). This matches the score-5 anchor including feedback loops for error recovery; it is not score 4 because no validation checkpoint is missing.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed: the skill is a single-purpose conversational methodology whose entire body belongs inline. Structure is clean — a `<what-to-do>` overview split from `<supporting-info>`, well-labeled sections, and working internal anchor links ([Grounding](#grounding), [Pulling from the pile](#pulling-from-the-pile)) — so navigation is easy and nothing is buried. This matches the well-organized-sections case for a self-contained skill; there is no misplaced reference material that would drop it to score 4.	5 / 5
	Total	20 / 20 Passed

Description

50%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 communicates a clear, concrete capability (turning raw material into an article, paragraph by paragraph) but reads more like a label than a trigger description. It lacks any "when to use this" guidance, natural trigger synonyms, and explanation of the "exploit" jargon, so it would likely not surface reliably when users need it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user provides raw material (fragments, notes, transcripts, an unstructured pile) and wants it shaped into a finished article."

Remove or briefly gloss the internal jargon "exploit" and enumerate 2-3 more concrete actions (e.g., draft candidate openings, ground concepts in order, choose block formats) to raise specificity.

Include natural trigger terms and synonyms users would actually say — draft, essay, blog post, 整理素材, 成文 — to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	"把原始素材塑造成文章，一段一段地推进" names the domain and 1-2 concrete actions (shape raw material into an article, advance paragraph by paragraph), matching the score-3 anchor. It is above score 2 (which requires only generic actions) but below score 4 because it omits several capabilities the skill actually has (candidate openings, grounding, format decisions).	3 / 5
Completeness	The "what" is clear (turn raw material into an article, paragraph by paragraph), but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description; per the judging guidelines this caps completeness at 3. It is not score 2 because the "what" is concrete rather than vague.	3 / 5
Trigger Term Quality	Relevant keywords exist ("Writing", "原始素材", "文章"), but common natural variations a user would say — draft, essay, blog post, 整理素材, transcript — are missing, matching the score-3 anchor ("some relevant keywords but missing common variations or synonyms"). Not score 4, which requires good coverage with only a few terms missing.	3 / 5
Distinctiveness Conflict Risk	"Writing, exploit：把原始素材塑造成文章" is somewhat specific (raw-material-to-article shaping) but the leading generic word "Writing" and the unexplained jargon "exploit" leave overlap risk with other writing/editing skills, matching the score-3 anchor. It is not score 2 because the raw-material framing does distinguish it from generic document helpers.	3 / 5
	Total	12 / 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: vinvcn/mattpocock-skills-zh-CN
Path: skills/in-progress/writing-shape/SKILL.md
Commit: 3f92a83

Reviewed: 4 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.