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

73%

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/docs-generator/SKILL.md

Quality

Content

67%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 well-structured and actionable with concrete template selection, output conventions, and clear reference pointers, but it is held back by redundancy between the body and the reference files and by some restated concepts.

Suggestions

De-duplicate the flavor/overlay selection table and the vendor-report MUST statements: keep them only in references/vendor-report-rules.md and link to them from the body to improve token efficiency.

Remove or tighten duplicated sections such as the repeated 触发时机 list and the generic progressive-disclosure layer table that restate concepts Claude already knows.

Add one short inline report skeleton or filename example in the body so the core action is copy-paste ready without requiring a round-trip to the reference files.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but carries notable redundancy: the flavor/overlay selection table and vendor-report MUST statements are repeated between the body and references, the 触发时机 list is duplicated, and sections like the progressive-disclosure layer table restate concepts Claude already knows.	3 / 5
Actionability	Provides concrete guidance including a task-to-template selection table, an exact filename format ('YYYY-MM-DD_[类型]-[目标简称]-report.md'), specific reference paths, a flavor selection table, and recommended Mermaid chart types; minor gap is the absence of any inline runnable example or sample report skeleton.	4 / 5
Workflow Clarity	Clear sequenced workflow via the 'ACTION REQUIRED' NOW/NEXT/ACT steps, 触发时机, 模板选择, 输出规范, 质量要求, and a completion self-check checklist; validation is mostly a final checklist rather than embedded validate→fix→retry checkpoints, leaving minor gaps.	4 / 5
Progressive Disclosure	SKILL.md serves as an overview pointing to three real, one-level-deep reference files (security-report-templates.md, vendor-report-rules.md, templates.md) via clearly signaled tables and inline links; structure is good, though some flavor/structure content is duplicated inline rather than kept solely in the references.	4 / 5
	Total	15 / 20 Passed

Description

78%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 clearly answers both what the skill does and when to use it, with a strong bilingual trigger-keyword list. Specificity and distinctiveness are slightly held back by the broad dual-domain scope and relatively high-level action language.

Suggestions

Replace generic action verbs with a concrete multi-action list (e.g., 'Generate READMEs, API reference docs, architecture docs, and formatted security/CTF writeups') to lift specificity toward the score-5 anchor.

Narrow or disambiguate the trigger terms so generic words like 'report' and 'documentation' are qualified (e.g., 'technical report' / 'CTF writeup') to reduce overlap with general writing skills.

Dimension	Reasoning	Score
Specificity	Names the documentation domain and a couple of concrete actions ('Creates task-oriented technical documentation', 'generate a formal report'), but does not enumerate a comprehensive set of specific actions like the score-5 anchor; the described actions are relatively high-level.	3 / 5
Completeness	Explicitly answers both what ('Creates task-oriented technical documentation', 'generate a formal report') and when ('Use when writing READMEs, API docs...'; 'at the END of any completed reverse engineering, penetration testing, CTF, or security analysis task') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong keyword coverage with an explicit 'Trigger keywords' list including Chinese synonyms (写报告, 写文档, 出报告) and English terms (writeup, report, documentation) plus 'Use when writing READMEs, API docs'; a few natural variations are missing but coverage is good.	4 / 5
Distinctiveness Conflict Risk	Largely distinct niche with specific triggers, but the dual scope (general documentation plus security reporting) and generic terms like 'report'/'documentation' create minor overlap risk with related writing and security skills.	4 / 5
	Total	16 / 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: zhaoxuya520/reverse-skill
Path: skills/docs-generator/SKILL.md
Commit: 7e2097f

Reviewed: 9 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.