writing-chapters

Use when writing paper chapters - requires completed brainstorming, writes one chapter at a time with user confirmation

Quality

72%

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/writing-chapters/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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 strong, highly actionable instruction skill with excellent workflow clarity (gates, checklists, two-stage review, feedback loops). Its main weakness is progressive disclosure: everything is packed into one monolithic file with no offloading to reference files, alongside some redundancy that hurts conciseness.

Suggestions

Move the detailed chapter-type guidance (Introduction, Literature Review, Methods input-to-output flow, Results/Discussion) and the two-stage review tables into a references/ file (e.g. CHAPTER_GUIDE.md), keeping SKILL.md as a lean overview with one-level-deep links.

Deduplicate the writing flow: keep either the dot flowchart or the checklist as the canonical sequence, and cross-reference rather than restating the de-AI rules in multiple sections.

Verify that referenced external paths like skills/brainstorming-research/templates.md actually resolve, or describe them as sibling-skill references rather than bundle files.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance that does not explain concepts Claude already knows, but it is long and redundant in places: the writing flow appears as both a dot graph and a checklist and a '写作前准备' section, and the de-AI rules recur across the checklist and the 写作规范 section, so it could be tightened.	2 / 3
Actionability	For an instruction-only skill it gives copy-paste-ready guidance: exact file paths (plan/outline.md, chapters/XX-name.md, plan/chapter-agent-provenance.md), exact status codes (DONE/DONE_WITH_CONCERNS/NEEDS_CONTEXT/BLOCKED), concrete paragraph patterns (背景段：场景约束 → 研究矛盾 → 本章承接), and ready-made confirmation/presentation prompt templates.	3 / 3
Workflow Clarity	Multi-step chapter writing is explicitly sequenced with HARD-GATE preconditions, a per-chapter checklist, a two-stage review with pass/fail, a flowchart with decision diamonds and rewrite feedback loops, and dedicated error-handling branches, satisfying the explicit-validation-and-feedback-loop anchor.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and all detailed content — review tables, chapter-type guidance, templates, the flowchart — lives inline in a single ~340-line SKILL.md, so although sections are well-organized, content that could be split into reference files is not, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 is well-structured with an explicit 'Use when' trigger and clear constraints, giving it strong completeness. It is let down by narrow trigger-term coverage and only moderate specificity and distinctiveness relative to sibling writing skills.

Suggestions

Broaden trigger terms to include natural variations users say, e.g. 'thesis chapters', 'dissertation', 'manuscript', 'academic writing'.

List a couple more concrete capabilities (e.g. 'drafts Introduction, Methods, Results, Discussion chapters') to lift specificity toward the multi-action anchor.

Add a distinguishing cue that separates this skill from sibling writing skills (e.g. 'use after brainstorming-research; for per-chapter drafting, not literature review or evidence mapping').

Dimension	Reasoning	Score
Specificity	It names the domain ('writing paper chapters') and a couple of process actions ('requires completed brainstorming', 'writes one chapter at a time with user confirmation'), but these are process constraints rather than a comprehensive list of distinct concrete capabilities, so it falls short of the multi-action anchor at 3.	2 / 3
Completeness	It contains an explicit 'Use when writing paper chapters' trigger and states what it does ('writes one chapter at a time with user confirmation', 'requires completed brainstorming'), clearly answering both what and when with an explicit trigger clause.	3 / 3
Trigger Term Quality	'writing paper chapters' is a natural phrase a user might say, but the description misses common variations users would also use (thesis, dissertation, manuscript, academic writing), matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The chapter-writing niche with brainstorming preconditions is fairly specific, but the description does not distinguish it from the many sibling writing skills it depends on (writing-core, writing-humanities, literature-review, etc.), so overlap with similar skills remains possible.	2 / 3
	Total	9 / 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: Norman-bury/research-writing-skill
Path: skills/writing-chapters/SKILL.md
Commit: 6f79595

Reviewed: 10 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.