doc-coauthoring

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

1.60x

Quality

76%

Does it follow best practices?

Impact

90%

1.60x

Average score across 7 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/anthropic-doc-coauthoring/SKILL.md

The canonical home for this skill is doc-coauthoring in anthropics/skills

Quality

Content

62%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.

A well-sequenced, highly actionable co-authoring workflow with strong validation checkpoints and feedback loops. Its main weaknesses are verbosity (heavy restating and announcement-style narration) and a monolithic structure that inlines detail a progressive layout would offload to reference files.

Suggestions

Trim repeated 'Announce intention to...' / 'Inform them that...' narration and consolidate the duplicated Stage 3 sub-agent vs. no-sub-agent branches to roughly halve length.

Move per-stage detail (full question lists, section-by-section step mechanics) into reference files under references/ (e.g., stage1-context.md, stage2-refinement.md, stage3-testing.md) and link to them from a leaner SKILL.md overview.

Replace intent statements ('Announce intention to re-read the entire document') with direct imperatives ('Re-read the entire document and check for...') to tighten actionability further.

Dimension	Reasoning	Score
Conciseness	The body runs ~280 lines and repeatedly restates the same stage mechanics and announcement phrasings ('Announce intention to...', 'Announce that...'), with padded procedural narration a competent Claude would not need; noticeably verbose across many sections.	2 / 5
Actionability	Provides concrete executable guidance throughout — specific question counts (5-10, 5-20), explicit tool calls (`create_file`, `str_replace`), numbered steps per section, and clear curation examples — with only minor gaps since some guidance is phrased as intent rather than exact actions.	4 / 5
Workflow Clarity	Three stages are clearly sequenced with explicit exit conditions and transitions (Stage 1 exit, Stage 2 loop-until-done, Stage 3 reader-testing pass criteria), plus validation/feedback loops (gap checks, quality checks after 3 iterations, Reader Claude verification before completion).	5 / 5
Progressive Disclosure	The skill is a single monolithic SKILL.md with no bundle files in references/scripts/assets, yet it inlines a large amount of stage-by-stage detail that could live in separate files; section headers exist but no one-level-deep references are signaled, so structure is present but content is not split.	3 / 5
	Total	14 / 20 Passed

Description

91%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.

A strong description with explicit what/when guidance, rich natural trigger terms across many doc types, and concrete actions. Third-person voice is used consistently. Minor broadness in the documentation niche keeps distinctiveness just below perfect.

Suggestions

Consider adding a brief distinguishing clause (e.g., 'Use for substantial multi-section documents, not quick notes') to sharpen the niche and reduce overlap with lightweight writing tasks.

The phrase 'similar documentation tasks' is generic; pairing it with one or two more concrete examples would tighten specificity.

Dimension	Reasoning	Score
Specificity	Lists concrete actions like 'co-authoring documentation', 'transfer context, refine content through iteration', and 'verify the doc works for readers', covering several specific behaviors with minor gaps in breadth of concrete actions.	4 / 5
Completeness	Explicitly answers 'what' (guide users through a structured workflow for co-authoring documentation) and 'when' (Use when user wants to write documentation, proposals, technical specs, decision docs; Trigger when user mentions writing docs, creating proposals, drafting specs) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases and synonyms across doc types — 'write a doc', 'draft a proposal', 'create a spec', 'write up', 'PRD', 'design doc', 'decision doc', 'RFC' — comprehensive coverage of how users actually ask for this.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (structured co-authoring workflow for documentation) with distinct triggers, but the broad documentation domain could have minor overlap with general writing/editing skills.	4 / 5
	Total	18 / 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: boisenoise/skills-collections
Path: skills/anthropic-doc-coauthoring/SKILL.md
Commit: 19c310e

Reviewed: about 20 hours 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.