skill-debate

Structured multi-provider AI debates between Claude and available advisors — use for critical decisions

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-debate/SKILL.md

Quality

Content

63%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 highly actionable with concrete commands, a well-sequenced workflow, and real validation checkpoints, but it suffers from significant duplication and lacks progressive disclosure — everything is inlined in one large file with no bundle files to offload detail.

Suggestions

De-duplicate the repeated sections (octopus banner, quality-gates table, cost tracking, export) that each appear twice in the body to recover token budget.

Move the quality-gates detail, cost-tracking tables, and export/integration sections into reference files under references/ and link to them, improving progressive disclosure.

Define or populate the placeholder variables (USER_GOAL, USER_PRIORITY, USER_CONSTRAINTS, CONTEXT, MAX_WORDS) used in the bash snippets so the guidance is fully executable.

Dimension	Reasoning	Score
Conciseness	Mostly actionable content rather than concept re-explanation, but the ~700-line body duplicates sections verbatim (the octopus banner, the quality-gates table, cost tracking, and export each appear twice), which is unnecessary padding that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready bash with concrete plugin script paths, a full flag table, and AskUserQuestion code, but several snippets reference undefined variables (USER_GOAL, USER_PRIORITY, USER_CONSTRAINTS, CONTEXT, MAX_WORDS) leaving minor gaps.	4 / 5
Workflow Clarity	Steps 1-7.5 are clearly sequenced with explicit validation (provider availability check, two-provider minimum enforcement, quality-gate re-prompt feedback loop) and a final checklist, but round 2+ handling is less detailed than round 1, a minor gap.	4 / 5
Progressive Disclosure	Has section headers and clear external script references, but with no bundle files present the entire ~700-line body is inlined in SKILL.md including content that could live in separate files (quality gates, cost tracking, export, examples), so it is structured but not split.	3 / 5
	Total	14 / 20 Passed

Description

62%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 communicates a distinct niche (multi-provider AI debates) and answers both what and when, but the trigger language is generic ('critical decisions') and lacks concrete user-facing trigger phrases and synonyms. It is solid but not comprehensive.

Suggestions

Add concrete trigger phrases users would actually say, e.g. 'use when the user asks for multiple perspectives, a second opinion, or wants advisors to review a decision'.

List more concrete actions (e.g. 'consult external advisors, run structured rounds, synthesize recommendations') to lift specificity beyond one action.

Replace the generic 'critical decisions' trigger with specific scenarios (PR review, architecture trade-offs, technical decisions) to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-provider AI debates') and one concrete action (debates between Claude and advisors), but stops there without listing synthesize/review/deliverable actions, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Explicitly answers both what ('Structured multi-provider AI debates...') and when ('use for critical decisions'), but the 'when' is generic rather than concrete trigger phrases, fitting the 'both present, when could be more specific' anchor rather than a 5.	4 / 5
Trigger Term Quality	Includes relevant keywords ('debates', 'advisors', 'critical decisions') but misses common natural variations users would say like 'get multiple perspectives', 'second opinion', or 'review', so it falls at 'some relevant keywords but missing synonyms'.	3 / 5
Distinctiveness Conflict Risk	The multi-provider debate niche is mostly distinct with low conflict risk, but the generic 'use for critical decisions' clause could overlap with general decision/review skills, placing it just below the fully-distinct anchor.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (728 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-debate/SKILL.md
Commit: 1bee725

Reviewed: 4 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.