CtrlK
BlogDocsLog inGet started
Tessl Logo

cognitive-doc-design

Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.

64

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./internal/assets/skills/cognitive-doc-design/SKILL.md
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.

The body is well-organized, concise, and actionable with a usable template and real commands, scoring consistently across dimensions. Adding a worked example and an explicit validation/feedback step would lift actionability and workflow clarity to the top level.

Suggestions

Add one short worked example showing the documentation template populated with real content to demonstrate the critical patterns applied end-to-end.

Include an explicit validation step in the workflow (e.g., 'Re-read the Quick path as a reviewer; if the decision is not first, revise') to create a feedback loop.

Trim the "When to Use" bullet list since the frontmatter trigger clause already covers the same doc types, reducing token redundancy.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explaining what a README/RFC is), with a dense patterns table and a copy-paste template; minor duplication between the "When to Use" list and the frontmatter trigger keeps it just short of fully lean.

4 / 5

Actionability

It provides a copy-paste documentation template and two executable bash commands, plus concrete pattern rules; the gap is the absence of a fully worked example applying the patterns end-to-end.

4 / 5

Workflow Clarity

The Documentation Shape gives a clear structural sequence (title, paragraph, Quick path, Details, Checklist, Next step) with a verification checklist, but there is no explicit validate-then-fix feedback loop, which the top anchor expects.

4 / 5

Progressive Disclosure

The body is self-contained with clean, well-labeled sections and no need for external references; it sits just below the top anchor because the body slightly exceeds the under-50-line simple-skill threshold.

4 / 5

Total

16

/

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 is strong: it pairs a clear purpose with an explicit, multi-term trigger clause, cleanly answering both what and when. Specificity is the weakest axis because only one concrete action is stated.

DimensionReasoningScore

Specificity

"Design docs that reduce cognitive load" names the domain and one concrete action with a specific intent, but offers only a single action rather than a comprehensive list, matching the 1-2 concrete-actions anchor.

3 / 5

Completeness

It explicitly answers both what ("Design docs that reduce cognitive load") and when (an explicit "Trigger:" clause with concrete trigger phrases), matching the both-answered-with-trigger-phrases anchor.

5 / 5

Trigger Term Quality

The explicit "Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs" lists six natural terms users would say, giving good coverage though general terms like "documentation"/"docs" are absent.

4 / 5

Distinctiveness Conflict Risk

The cognitive-load design framing and doc types (RFCs, architecture, onboarding, review-facing) form a mostly distinct niche with only minor overlap risk against closely related general writing skills.

4 / 5

Total

16

/

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
Gentleman-Programming/gentle-ai
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.