skill-debate

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

Quality

76%

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

77%Weight 40%Scale 1-3

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 and clearly sequenced with real validation feedback loops. Its weaknesses are verbosity from duplicated sections and a monolithic structure with no progressive disclosure into reference files.

Suggestions

De-duplicate the body: the visual banner, the flags table, and the quality-gates table each appear twice — keep one canonical copy and cross-reference it.

Move stable reference material (full flags table, quality-gate metric definitions, cost-tracking/export details) into reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Trim repeated emphasis language ("MANDATORY", "PROHIBITED", "NOT optional", banner callouts) to reduce token cost without losing the binding instructions.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable with concrete commands, but it is padded with redundancy — the visual banner, the flags table, and the quality-gates table each appear twice — plus heavy repeated emphasis language, so it could be tightened rather than earning the lean level-3 anchor.	2 / 3
Actionability	It provides abundant copy-paste-ready executable bash (orchestrate.sh spawn, mkdir/heredoc setup, build-fleet.sh, quality-gate functions) with specific examples, matching the fully-executable level-3 anchor.	3 / 3
Workflow Clarity	Steps 1–7.5 are clearly sequenced with explicit validation checkpoints (provider availability check, quality-gate scoring with a re-prompt feedback loop below 50), matching the level-3 anchor of clear sequence plus feedback loops for error recovery.	3 / 3
Progressive Disclosure	There are no bundle files (references/scripts/assets absent) and the ~700-line SKILL.md is monolithic, with content that should be split out (flag reference, quality-gate detail) kept inline and even duplicated, matching the level-2 anchor of some structure but content that should be separate is inline.	2 / 3
	Total	10 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 cleanly states what the skill does and when to use it with an explicit trigger clause, and occupies a distinctive niche. It is slightly held back by naming only one action and having a somewhat thin set of trigger-term variations.

Suggestions

Add one or two more concrete verbs to the description (e.g. "runs, compares, and synthesizes multi-provider AI debates") to reach the level-3 specificity anchor.

Broaden trigger terms to include natural phrasings like "compare options", "get diverse perspectives", or "review with multiple models".

Dimension	Reasoning	Score
Specificity	It names the domain and a concrete action — "Structured multi-provider AI debates between Claude and available advisors" — but describes a single activity rather than listing multiple specific concrete actions, so it stops short of the level-3 anchor.	2 / 3
Completeness	It answers both what ("Structured multi-provider AI debates between Claude and available advisors") and when via an explicit trigger clause ("use for critical decisions"), satisfying the level-3 anchor and avoiding the missing-trigger cap.	3 / 3
Trigger Term Quality	"debates", "critical decisions", and "advisors" are natural terms a user might say, but coverage of common phrasings (e.g. "review", "compare options", "get perspectives") is limited, matching the level-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	"multi-provider AI debates" is a clear, narrow niche with distinct triggers unlikely to fire for unrelated skills, matching the level-3 anchor.	3 / 3
	Total	10 / 12 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 (717 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: 9f39f0c

Reviewed: 10 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.