docs-generator

Creates task-oriented technical documentation with progressive disclosure. Use when writing READMEs, API docs, architecture docs, or markdown documentation. Also use this skill at the END of any completed reverse engineering, penetration testing, CTF, or security analysis task to generate a formal report in the user's project directory. Trigger keywords: 写报告, 写文档, 出报告, writeup, 技术文档, report, documentation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%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.

A well-organized, actionable body that routes users to real template files with concrete filename and output-location rules, clear sequencing, and a completion checklist. Its main weakness is redundancy: several output/quality sections duplicate content already in the bundled reference, and it explains some generic concepts Claude already knows.

Suggestions

Remove the duplicated '输出规范'/'质量要求' content from SKILL.md and point to the corresponding section in references/security-report-templates.md instead, keeping the body lean.

Trim generic explanatory material (the Progressive Disclosure layer table, 'Show, Don't Tell') that Claude already knows, retaining only task-specific guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured, but the '输出规范'/'质量要求'/'输出时机' sections duplicate content already present in references/security-report-templates.md, and it spends tokens explaining general concepts Claude already knows (e.g., the generic Progressive Disclosure layer table, 'Show, Don't Tell'), so it is 'mostly efficient but could be tightened'.	2 / 3
Actionability	Provides concrete, executable guidance — a template-selection table mapping task types to specific reference files, a copy-paste-ready filename format ('YYYY-MM-DD_[类型]-[目标简称]-report.md'), explicit output-location rules, and links to real template files — matching the anchor for fully actionable, specific examples.	3 / 3
Workflow Clarity	Sequences the work via the 'ACTION REQUIRED' (NOW/NEXT/ACT) block and closes with an explicit '任务完成自检' completion checklist; for this non-destructive file-writing task the checklist serves as the validation checkpoint, matching the anchor for a clear sequence with checklists for a complex process.	3 / 3
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references to two real, verified bundle files (references/security-report-templates.md and references/templates.md) via a template-routing table and inline links, with template content appropriately split out rather than inlined, matching the highest anchor.	3 / 3
	Total	11 / 12 Passed

Description

92%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.

A strong, well-structured description with concrete actions, explicit when-triggers, and excellent natural-keyword coverage (including bilingual terms). Its main weakness is a dual purpose that blurs its niche and raises mild conflict risk with other documentation skills.

Suggestions

Tighten the description around a single primary niche or add a sharper differentiator so generic documentation keywords do not collide with other documentation skills.

Consider dropping or qualifying the generic 'documentation/markdown documentation' triggers if the skill's true distinctive value is security/reverse-engineering report generation.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Creates task-oriented technical documentation', 'writing READMEs, API docs, architecture docs', and 'generate a formal report' — matching the anchor that lists several specific actions rather than vague language.	3 / 3
Completeness	Explicitly answers both WHAT ('Creates task-oriented technical documentation... generate a formal report') and WHEN ('Use when writing READMEs...'; 'Also use this skill at the END of any completed reverse engineering...'), with explicit triggers, matching the highest anchor.	3 / 3
Trigger Term Quality	Includes both a 'Use when...' clause and an explicit natural-keyword list ('READMEs, API docs, architecture docs' plus '写报告, 写文档, 出报告, writeup, report, documentation'), giving strong coverage of terms users would actually say, including bilingual variants.	3 / 3
Distinctiveness Conflict Risk	The skill serves two fairly different purposes — general technical docs AND security reporting — and generic doc keywords ('documentation', 'markdown documentation', 'READMEs') could overlap with other documentation skills, so it is 'somewhat specific but could still overlap' rather than having a single unambiguous niche.	2 / 3
	Total	11 / 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: zhaoxuya520/reverse-skill
Path: skills/docs-generator/SKILL.md
Commit: 6aa1362

Reviewed: 7 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.