CtrlK
BlogDocsLog inGet started
Tessl Logo

documentation-standards

Scaffolds issue docs, ADRs, README outlines, changelog entries, roadmap updates, Mermaid architecture diagrams using project templates. Use when drafting ADR, writing changelog, updating roadmap after a feature ships, creating README for a new library, or diagramming a system flow.

66

Quality

78%

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 ./src/orchestrator/skills/documentation-standards/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 tightly written, highly actionable reference for documentation formats whose main defects are a dangling reference to a missing WRITING-GUIDE.md, an unspecified formatter command, and the absence of validation feedback loops. The format templates themselves are exemplary in their concreteness and economy.

Suggestions

Ship the referenced WRITING-GUIDE.md (or move its writing guidelines and anti-patterns into a references/ file that actually exists) so the body's primary pointers are not dead ends.

Replace "Resolve the formatter command via the **codebase-tool** slot" with the concrete formatter invocation, or an explicit example of how to resolve it.

Add a short feedback loop to the Validate section: what to do when markdown-link-check reports broken links (fix, re-run, only commit on exit 0).

DimensionReasoningScore

Conciseness

The ~28-line body is lean and dense: exact headings, field lists, enum values, and one executable command, with zero explanation of concepts Claude already knows — every token earns its place.

5 / 5

Actionability

The templates are highly concrete (exact fields, statuses, ordering rules) and the link-check command is executable, but "Resolve the formatter command via the **codebase-tool** slot" withholds the actual formatter command, leaving a minor execution gap.

4 / 5

Workflow Clarity

The roadmap-completion flow has a sequence and the Validate section names a checkpoint ("Check links and formatting before committing"), but most sections are format references rather than sequenced procedures and there is no fix-and-retry feedback loop when validation fails.

3 / 5

Progressive Disclosure

The body points to "WRITING-GUIDE.md, beside this file" and ".opencastle/project/docs-structure.md", but neither file exists in the skill bundle (no references/ directory or WRITING-GUIDE.md present), so the primary pointers to writing guidelines and anti-patterns dead-end.

2 / 5

Total

14

/

20

Passed

Description

88%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: concrete third-person capability list paired with an explicit, trigger-rich "Use when" clause covering every sub-task. Only minor gaps in synonym coverage and slight overlap risk with general writing skills.

DimensionReasoningScore

Specificity

"Scaffolds issue docs, ADRs, README outlines, changelog entries, roadmap updates, Mermaid architecture diagrams using project templates" names six concrete deliverables in third person, comprehensively covering the skill's domain with no notable gaps.

5 / 5

Completeness

It explicitly answers both what ("Scaffolds issue docs, ADRs, README outlines...") and when ("Use when drafting ADR, writing changelog...") with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

"drafting ADR, writing changelog, updating roadmap after a feature ships, creating README for a new library, or diagramming a system flow" provides good natural keyword coverage, but a few natural terms are missing (e.g., "architecture decision record" spelled out, "release notes", "documentation").

4 / 5

Distinctiveness Conflict Risk

The specific artifact types (ADR, changelog, roadmap, Mermaid diagrams) give it a clear niche, but triggers like "writing changelog" and "creating README" carry minor overlap risk with generic writing or commit-message skills.

4 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
monkilabs/opencastle
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.