CtrlK
BlogDocsLog inGet started
Tessl Logo

doc-coauthoring

A structured workflow for co-authoring high-signal docs (PRD, RFC, design docs, proposals, decision records). Use when the user needs to turn messy context into a readable artifact with clear goals, tradeoffs, and next steps. Emphasizes context capture, outline-first drafting, and context-free reader testing to catch blind spots.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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-structured, actionable instruction-only skill with a clear 3-stage workflow, explicit feedback loops, and an appropriately externalized templates reference. It consistently lands at 'good with minor gaps' rather than excellent across all four dimensions.

Suggestions

Trim or merge the 'Quality Bar' section, since its questions duplicate Stage 1's success criteria and Stage 3's reader-testing output — fold any unique points into the relevant stages to remove redundancy.

Add one short worked example (e.g., a sample context snapshot or a 3-7 bullet section intent) so the Stage 1 output and Stage 2 loop are unambiguous on first use.

Make the templates reference a clickable markdown link (e.g., 'Load [references/templates.md](references/templates.md)') and add a brief note on when to loop back to an earlier stage if reader testing surfaces missing context.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence, but the 'Quality Bar' section re-asks questions already covered in Stage 1 (success criteria) and Stage 3 (reader testing), a minor instance of over-explanation that could be trimmed — anchor 4 rather than 5.

4 / 5

Actionability

Provides concrete, ready-to-use guidance — the Stage 3 review prompt is copy-paste ready, Stage 1 lists seven specific questions, and Stage 2 gives a numbered iteration loop — but lacks a worked example (e.g., a filled-in context snapshot or section intent), leaving minor gaps versus anchor 5.

4 / 5

Workflow Clarity

Three clearly sequenced stages each carry a Goal and Output, with an explicit feedback loop in Stage 2 (draft → review → revise) and a validation step in Stage 3 (reader testing producing a fix list), but cross-stage error recovery (e.g., returning to Stage 1 when Stage 3 reveals missing context) is implied rather than explicit — anchor 4.

4 / 5

Progressive Disclosure

The body is a well-organized overview that externalizes detail into the one-level-deep references/templates.md, signaled clearly via 'Load references/templates.md and pick the closest template', but the reference is a plain path rather than a clickable link and the Quality Bar section mildly overlaps earlier content — anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

87%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 that clearly states both capability and trigger conditions with concrete document-type keywords. It is held back from a perfect score only by mildly abstract process vocabulary and a few missing synonyms in trigger coverage.

DimensionReasoningScore

Specificity

Names the domain plus several concrete actions — 'context capture, outline-first drafting, and context-free reader testing' and 'turn messy context into a readable artifact' — but the actions are process-level rather than discrete operations, and phrases like 'high-signal docs' and 'messy context' are mildly abstract, so it sits at anchor 4 rather than 5.

4 / 5

Completeness

Explicitly answers both what ('A structured workflow for co-authoring high-signal docs...') and when ('Use when the user needs to turn messy context into a readable artifact with clear goals, tradeoffs, and next steps'), matching the anchor 5 requirement for concrete trigger phrases on both axes.

5 / 5

Trigger Term Quality

Good natural keyword coverage via 'PRD, RFC, design docs, proposals, decision records' and 'co-authoring', but common synonyms like 'spec', 'memo', 'write-up', or 'one-pager' are missing, placing it just below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche — structured co-authoring of PRD/RFC/design-doc/proposal/decision-record artifacts via a named 3-stage workflow — with a specific trigger unlikely to fire for unrelated skills, matching the anchor 5 'clear niche with distinct triggers'.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
shareAI-lab/Kode-CLI
Reviewed

Table of Contents

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.