skill-debate

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

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

58%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 content has an excellent, well-validated workflow with concrete executable commands, but it is bloated by duplication and lacks any progressive disclosure — all reference material is inlined into a single ~715-line file.

Suggestions

Remove the duplicated Quality Gates table and the duplicated provider-availability banner; keep a single authoritative copy of each.

Split bulk reference material (flag reference, provider CLI syntax caveats, quality-gate scoring function, cost/export tables) into files under references/ and link to them one level deep, trimming SKILL.md to a lean overview.

Consolidate the repeated MANDATORY/CRITICAL/PROHIBITED compliance sections into one concise 'Compliance' block to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The ~715-line body is noticeably verbose: the Quality Gates metric table appears twice, the provider-availability banner is duplicated, and multiple MANDATORY/CRITICAL sections restate the same dispatch rule, padding tokens beyond what Claude needs.	2 / 5
Actionability	Provides mostly executable bash snippets (orchestrate.sh spawn, build-fleet.sh, mkdir/cat heredocs) with concrete flags and case branches; minor gaps are placeholder variables (USER_GOAL, CONTEXT) the author must resolve.	4 / 5
Workflow Clarity	Clear 7-step sequence with explicit validation checkpoints (provider availability check, per-response quality gates with re-prompt on score<50, flag-precedence validation errors) and feedback loops for the batch/multi-advisor dispatch.	5 / 5
Progressive Disclosure	No references/, scripts/, or assets/ bundle files exist and the body inlines everything (full provider syntax, quality-gate logic, cost tables, examples) into one monolithic SKILL.md with no one-level-deep references to split out the bulk.	2 / 5
	Total	13 / 20 Passed

Description

61%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 clear and reasonably distinct, establishing a niche (multi-provider AI debates) with a brief trigger clause. It is held back by limited concrete-action enumeration and thin trigger-term coverage.

Suggestions

Expand the description to list 3-4 concrete actions (e.g., '...run structured rounds between external advisors and Claude, cross-critique proposals, and synthesize a recommendation').

Add explicit natural trigger phrases such as 'Use when the user wants a second opinion from multiple AI models, asks to debate a decision, or wants Codex/Antigravity to review something'.

Sharpen the 'when' clause beyond 'critical decisions' to reduce overlap with generic review skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-provider AI debates between Claude and available advisors') and the synthesize action, but stops at 1-2 concrete actions without listing the full debate lifecycle (rounds, cross-critique, synthesis, deliverables).	3 / 5
Completeness	Has a clear 'what' ('Structured multi-provider AI debates between Claude and available advisors') and a terse 'when' ('use for critical decisions'); the 'when' is explicit but thin and could be more specific about trigger phrases.	4 / 5
Trigger Term Quality	Includes some natural terms ('debates', 'advisors', 'critical decisions') but lacks common user phrasings and synonyms like 'second opinion', 'review with multiple models', or 'compare AI opinions'.	3 / 5
Distinctiveness Conflict Risk	The 'multi-provider AI debates' niche is mostly distinct from other skills with only minor overlap risk against generic 'review' or 'decision' skills, though 'critical decisions' alone is somewhat broad.	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 (716 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: bc76e7c

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.