council-verdicts

Starter: interpret a council run's verdict artifacts — quorum, dissent, cross-lab validity, and what to do next

Quality

78%

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/octopus-starter-pack/council-verdicts/SKILL.md

Quality

Content

92%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 tight, well-structured instruction-only skill: lean prose, concrete file paths and decision rules, explicit error-handling branches, and clean section organization. The only improvements are minor specificity details like the location of the gate's usage log and a definition of the session window.

Dimension	Reasoning	Score
Conciseness	The ~27-line body is lean with zero padding: every line carries skill-specific knowledge (artifact paths, seat semantics, the SubagentStop gate) and nothing Claude already knows is explained, matching the 'every token earns its place' anchor.	5 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill — exact paths ('~/.claude-octopus/results/', 'summary.json', 'hooks/subagent-stop-gate.sh'), explicit verdict labels (APPROVE/REJECT/ABSTAIN/REVISE), and a tally-to-action mapping — with minor gaps such as where the gate's usage log lives and what 'within the session window' means.	4 / 5
Workflow Clarity	Five steps are clearly sequenced with explicit validation branches ('If none exist within the session window, say so; never invent a verdict', malformed verdicts count as ABSTAIN, factual disagreement triggers a recommended re-run), and the read-only task carries no destructive/batch validation cap.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ bundle exists), and its well-organized sections (When to use / Steps / Guardrails) meet the rubric's simple-skill exception for a top score.	5 / 5
	Total	19 / 20 Passed

Description

65%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 concise, specific to a distinct niche, and written in third person, but it omits any 'when to use this skill' trigger guidance, which caps completeness. Adding a 'Use when a /octo:council run finishes and the user asks what the council decided' clause would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when a /octo:council run has finished and the user asks what the council decided or pastes a summary.json path.'

Replace the vague 'what to do next' with a concrete action such as 'recommend the next step (proceed, proceed with follow-ups, or re-run)' to strengthen specificity.

Add one or two natural trigger synonyms (e.g. 'council results', 'verdict tally') to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('council run's verdict artifacts') and concrete sub-topics ('quorum, dissent, cross-lab validity'), but the action coverage rests on a single verb ('interpret') plus the generic 'what to do next' — closer to anchor 3 than anchor 4's 'several specific actions'.	3 / 5
Completeness	The 'what' is clear (interpret verdict artifacts — quorum, dissent, cross-lab validity, next steps) but there is no 'Use when...' clause or equivalent trigger guidance, which the judging guidelines explicitly cap at 3; the body's 'When to use' section does not count toward the frontmatter description.	3 / 5
Trigger Term Quality	'council run', 'verdict', 'quorum', 'dissent' are natural terms a user of this ecosystem would say, giving good keyword coverage; a few natural variations ('results', 'decision', 'summary.json') are missing, so it falls short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	'council run's verdict artifacts', 'quorum', 'dissent', 'cross-lab validity' define a clear niche with distinct triggers and virtually no overlap risk with other skills.	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: skills/octopus-starter-pack/council-verdicts/SKILL.md
Commit: 0093dab

Reviewed: 5 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.