Name: doc-coauthoring
Rating: 48 (1 reviews)
Author: administrakt0r

doc-coauthoring

This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.

Quality

51%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/doc-coauthoring/SKILL.md

The canonical home for this skill is doc-coauthoring in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

56%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 a thorough, well-sequenced co-authoring workflow with concrete tool calls and feedback loops, but it is verbose with duplicated passages and keeps all detail inlined in SKILL.md rather than splitting it into reference files.

Suggestions

Deduplicate the Stage 3 testing instructions shared between the sub-agent and manual paths, and remove repeated placeholder-creation narration.

Move the detailed per-stage scripts and the manual testing checklist into reference files (e.g., references/stage-details.md, references/reader-testing.md) and link to them from SKILL.md.

Trim padded narration ('Inform them...', 'Announce intention to...') to instruction-level directives that assume Claude's competence.

Dimension	Reasoning	Score
Conciseness	The ~370-line body is noticeably verbose, with duplicated instructions (e.g., placeholder-creation steps and Stage 3 testing restated nearly verbatim for sub-agent and manual paths) and padded narration like 'Advise them not to worry about organizing it - just get it all out.'	2 / 5
Actionability	Provides concrete executable guidance — specific tool calls (create_file, str_replace), numbered brainstorm ranges, concrete curation examples, and a real URL — with only minor gaps where guidance stays abstract (e.g., 'Generate 5-10 numbered questions').	4 / 5
Workflow Clarity	A clear three-stage sequence with explicit sub-steps, exit conditions, transitions, and feedback loops (reader testing loops back to refinement; iteration-count quality check), though validations are conversational confirmations rather than hard checks.	4 / 5
Progressive Disclosure	No bundle files exist and the entire workflow is inlined monolithically in SKILL.md; section headers give reasonable in-file structure, but substantial content (per-stage scripts, duplicated testing instructions) that could live in separate references is inline with no external navigation.	3 / 5
	Total	13 / 20 Passed

Description

47%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 conveys what the skill does via its three named stages, but it omits any explicit 'when to use' trigger guidance and lacks the natural trigger phrases that would help it fire for the right requests.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases (e.g., 'Use when the user wants to write or draft a doc, proposal, PRD, design doc, decision doc, or RFC').

Include natural user phrasings like 'write a doc', 'draft a proposal', 'write up', and 'spec' so the description surfaces on real requests.

Tighten the distinctiveness by framing the niche as collaborative/iterative co-authoring rather than generic 'document creation'.

Dimension	Reasoning	Score
Specificity	Names the domain (collaborative document creation) and enumerates concrete named stages (Context Gathering, Refinement & Structure, Reader Testing), listing several specific components with minor gaps in coverage.	4 / 5
Completeness	The 'what' is clear (a three-stage co-authoring workflow), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Only generic phrasing ('document creation', 'collaborative document creation') appears; the natural trigger phrases users actually say (e.g. 'write a doc', 'draft a proposal', 'PRD') are absent from the description despite appearing in the body.	2 / 5
Distinctiveness Conflict Risk	The three-stage co-authoring framing is somewhat specific, but 'document creation' is broad and overlaps with many writing/document skills, and no trigger phrases sharpen the niche.	3 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/doc-coauthoring/SKILL.md
Commit: 57c135b

Reviewed: 3 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.