writing-shape

Writing, exploit——把原始素材塑造成文章，一段一段地推进。

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/in-progress/writing-shape/SKILL.md

Quality

Content

85%

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 tight, well-structured process skill with concrete moves, decision thresholds, and explicit validation/feedback loops. Its only weakness is mild redundancy between the loop steps and the grounding section, which keeps conciseness at the midpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and teaches a genuinely novel methodology without explaining concepts Claude already knows, but the grounding mechanism and the phrase 'what does the reader need to hear next?' are restated across 'The loop' and the 'Grounding' section, so it could be tightened to reach anchor 3.	2 / 3
Actionability	It gives concrete, executable guidance: a numbered 6-step loop, verbatim conversational moves to use, concrete format tradeoffs with thresholds (e.g. 'repeats 3+ times → table'), and specific callout syntax ("> [!TIP]", "> [!NOTE]") — fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	A clearly sequenced 6-step loop with explicit validation checkpoints: the grounded-concepts checklist that blocks ungrounded dependencies, the 'draft 2-3 openings and force a choice' gate, and the re-read-from-disk-before-writing feedback loop to avoid blind overwrites.	3 / 3
Progressive Disclosure	No bundle files are needed or present, and the content is well-organized into clearly titled sections with signaled internal anchor links ([Grounding](#grounding), [Pulling from the pile](#pulling-from-the-pile)) and no nested references, satisfying the simple-skill allowance for a 3.	3 / 3
	Total	11 / 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 conveys the skill's purpose compactly and names a concrete action, but it omits any explicit "when to use" trigger and relies on framework jargon ("exploit") that users would not naturally say. It is uniformly at the midpoint across all four dimensions.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when turning raw notes, transcripts, or fragments into a finished article, paragraph by paragraph.'

Replace or gloss the jargon term 'exploit' with user-facing language and include common variations like 'draft', 'essay', 'blog post', or 'shape notes into an article' to improve trigger-term coverage.

List a couple more concrete actions (e.g. 'draft openings, sequence paragraphs, choose prose vs. list vs. table formats') to raise specificity toward anchor 3.

Dimension	Reasoning	Score
Specificity	It names the domain ("Writing" / "article") and one concrete action — "把原始素材塑造成文章，一段一段地推进" (shape raw material into an article, advancing paragraph by paragraph) — but does not list multiple specific concrete actions, so it falls short of anchor 3.	2 / 3
Completeness	It states what the skill does (shape raw material into an article) but provides no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	"Writing" and "article" are natural terms a user might say, but coverage is thin and "exploit" / "原始素材" are framework jargon users would not utter; common variations like "draft", "essay", or "turn notes into an article" are missing.	2 / 3
Distinctiveness Conflict Risk	Writing-from-raw-material is a recognizable niche, but the description lacks distinct triggers and could overlap with other general writing or ideation skills, matching anchor 2 rather than a clearly conflict-free niche.	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/in-progress/writing-shape/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.