writing-fragments

Writing, explore——挖掘原始 fragments，暂不施加任何结构。

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

100%

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, actionable, well-organized instruction set: it assumes Claude's competence, gives concrete capture/append guidance with a file-format example, and sequences the workflow with a re-read guard. It earns top marks across all content dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it defines only the skill-specific 'fragment' concept and gives tight rules plus a compact file-format example, with no padding about general concepts Claude already knows.	3 / 3
Actionability	Concrete, executable guidance throughout — '运行一个产出 fragments 的 grilling session', '从用户说的第一句话开始捕获', 'append to a single markdown file', and a worked file-format template with the '\n---\n' separator make the instructions copy-ready.	3 / 3
Workflow Clarity	As a single-purpose skill the sequence is unambiguous (ask path once → capture from first utterance → write H1+title → append each fragment), with an explicit re-read-before-write guard ('从磁盘重新读取文件…永远不要 overwrite') acting as a checkpoint against clobbering user edits.	3 / 3
Progressive Disclosure	A simple, self-contained skill (no bundle files exist) with clear top-level structure (<what-to-do> / <supporting-info>) and well-organized sections, so per the scoring notes well-organized sections suffice for a top score.	3 / 3
	Total	12 / 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 identifies a clear domain and stance but stops short of listing concrete actions or providing an explicit 'Use when…' trigger, which caps both completeness and distinctiveness at 2. Adding a third-person action list and a natural trigger clause would lift it toward the top of the scale.

Suggestions

Add 2–3 concrete third-person actions (e.g., 'Runs a grilling interview, captures fragments from the first utterance, appends them to a single markdown file') to raise specificity to 3.

Append an explicit 'Use when…' clause with natural user trigger phrases (e.g., 'Use when the user wants to brainstorm or gather raw writing fragments before structuring') to satisfy completeness and trigger-term quality.

Rephrase the mixed-language jargon ('挖掘原始 fragments') into natural terms a user would actually say, to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Quotes "explore——挖掘原始 fragments，暂不施加任何结构" name the writing/fragments domain and the explore stance, but list no concrete actions (e.g., interview, capture, append), matching the 'names domain and some actions, not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It conveys a partial 'what' (explore raw fragments, impose no structure) but has no 'when'/'Use when…' clause, so per the rubric guideline a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "Writing", "explore", "fragments" are relevant but mixed with technical phrasing ("挖掘原始 fragments") and lack common natural variations a user would actually say, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The explore-vs-structure framing carves a niche and is unlikely to fire for the wrong skill, but without explicit triggers it could still overlap with general brainstorming/writing skills, matching the 'somewhat specific but could still overlap' anchor.	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-fragments/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.