spec-loop-setup-doc-rendering

Help set up and troubleshoot rendering for task files and glossary files. Use when the user asks about PlantUML, AsciiDoc, VS Code, Cursor, other VS Code-based IDEs, JetBrains, preview rendering, Java, or Graphviz needed to review rendered task or glossary files.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/spec-loop-setup-doc-rendering/SKILL.md

Quality

Content

71%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 concise, actionable, and reasonably well-sequenced with concrete verification commands and confirmation gates. Its main weakness is progressive disclosure: the referenced setup documents do not exist in the bundle and the actual helper script is not named or linked.

Suggestions

Add the referenced vscode-setup.md and jetbrains-setup.md to references/ (or remove the broken links and inline the essentials) so the documented navigation actually resolves.

Name and link the existing helper script when directing Claude to 'the helper script check path' (e.g., run scripts/setup-vscode-server-based.sh --check) so the recommended path is reachable.

Present the gather -> report -> probe -> setup sequence as a numbered checklist with an explicit re-check-after-fix loop, and deduplicate the repeated 'For VS Code, Cursor, and other VS Code-based IDEs' phrasing.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no concept over-explanation, but the phrase 'For VS Code, Cursor, and other VS Code-based IDEs' recurs and a few policy lines could be tightened, keeping it just below the lean anchor 5.	4 / 5
Actionability	It gives concrete executable commands (`command -v dot`, `dot -V`, `java -version`, `test -f`) for the direct-check paths, but the preferred 'helper script check path' is never named or linked, leaving a minor gap that prevents a 5.	4 / 5
Workflow Clarity	A clear sequence is present (gather evidence -> report working/missing/unverifiable -> suggest probes -> follow setup path) with a confirmation gate before changing settings, though it is prose rather than a numbered checklist with an explicit re-check loop, so it is not a 5.	4 / 5
Progressive Disclosure	The body links to vscode-setup.md and jetbrains-setup.md as one-level-deep references, but neither file exists in the bundle and the one real bundle file (scripts/setup-vscode-server-based.sh) is never linked, so navigation is partly broken and organization has real gaps rather than minor ones.	3 / 5
	Total	15 / 20 Passed

Description

82%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 clearly and explicitly covers both what the skill does and when to use it, with strong natural trigger terms and a distinct niche. Its only weakness is that the named actions are generic rather than enumerating several specific concrete capabilities.

Dimension	Reasoning	Score
Specificity	The description names the domain (rendering for task/glossary files) and two actions ('set up and troubleshoot rendering'), matching the '1-2 concrete actions' anchor; it is not a 4 because the actions are generic rather than several specific concrete ones.	3 / 5
Completeness	It explicitly states both what ('Help set up and troubleshoot rendering for task files and glossary files') and when ('Use when the user asks about PlantUML, AsciiDoc, VS Code...') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	It lists strong natural keywords users would say (PlantUML, AsciiDoc, VS Code, Cursor, JetBrains, Graphviz, preview rendering, Java), but misses synonyms and file extensions like .puml and .adoc, so it falls short of the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The combination of task/glossary rendering with named tools (PlantUML, AsciiDoc, Graphviz, JetBrains) carves a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: dpolivaev/spec-loop
Path: skills/spec-loop-setup-doc-rendering/SKILL.md
Commit: 27df5cc

Reviewed: 19 days 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.