CtrlK
BlogDocsLog inGet started
Tessl Logo

docs-writer

Documentation workflow that converts requirements into structured AsciiDoc sections, runs Vale for style compliance, and produces merge-ready content. Use when creating or updating AsciiDoc documentation from Jira tickets, GitHub issues, or feature descriptions.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is docs-writer in flightctl/ai-workflows

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

An exemplary orchestrator body: lean routing logic, explicit error handling with an escalation path, and purpose-labeled pointers to detail files. The only deductions are minor — phase semantics and checkpoints live in external files, and those referenced files are absent from the bundle being evaluated.

DimensionReasoningScore

Conciseness

Every line is a routing decision or failure rule with zero padding; the body assumes Claude's competence and adds nothing it already knows, matching the lean anchor 5.

5 / 5

Actionability

Concrete executable guidance (read `commands/{command}.md`, check `.artifacts/${ticket_id}/`, read `skills/controller.md`) with clear branching, but "execute the `/gather` phase" defers its meaning entirely to an external file — a minor gap.

4 / 5

Workflow Clarity

The dispatch sequence is clearly numbered and includes an explicit failure checkpoint with retry/escalate feedback ("stop and report the error... Offer to retry... or escalate"), but success checkpoints for the phases themselves are deferred elsewhere, leaving minor validation gaps.

4 / 5

Progressive Disclosure

A clean overview with well-signaled, one-level-deep references, each with its purpose stated ("For principles, hard limits, safety, quality, and escalation rules, see `guidelines.md`"). However, none of the referenced files (`commands/`, `skills/controller.md`, `guidelines.md`) exist in the provided bundle, so navigation cannot be fully verified.

4 / 5

Total

17

/

20

Passed

Description

83%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: third-person voice, concrete named tools, and an explicit "Use when" clause with distinct trigger sources. The main gaps are missing common trigger variations (notably the .adoc file extension) and a slightly vague "merge-ready content" claim.

Suggestions

Add the .adoc file extension and common synonyms (e.g., "adoc files", "docs") to the trigger clause to improve natural-term coverage.

Clarify what "produces merge-ready content" means concretely (e.g., opens a pull request or passes CI checks) to remove the last vague claim.

DimensionReasoningScore

Specificity

Names three concrete actions with specific tools ("converts requirements into structured AsciiDoc sections", "runs Vale for style compliance", "produces merge-ready content"), but "merge-ready content" is slightly underspecified, matching anchor 4 rather than comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both what (three concrete actions) and when ("Use when creating or updating AsciiDoc documentation from Jira tickets, GitHub issues, or feature descriptions") with concrete trigger phrases, matching anchor 5.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("AsciiDoc documentation", "Jira tickets", "GitHub issues", "feature descriptions", "creating or updating") but misses common variations like ".adoc", "adoc", "docs", or "technical writing".

4 / 5

Distinctiveness Conflict Risk

The AsciiDoc/Vale/Jira niche is mostly distinct with clear trigger sources, but the generic "Documentation workflow" opening leaves minor overlap risk with other documentation-writing skills, fitting anchor 4 better than 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
amir-yogev-gh/ai-workflows
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.