octopus-research

Thorough research across multiple sources — use for complex topics needing broad synthesis

Quality

72%

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-deep-research/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with a clear, well-gated multi-step workflow and strong validation, but it is verbose due to repeated enforcement language and does not progressively disclose detail into separate reference files.

Suggestions

Collapse the redundant enforcement blocks (HARD-GATE, repeated 'CRITICAL/PROHIBITED' lists) into a single concise contract statement to reclaim tokens.

Move the banner template and parameter definitions into a referenced file (e.g. references/banner.md) and link to it, improving progressive disclosure.

Verify the external referenced paths (skills/blocks/codex-host-adapter.md, skill-security-framing.md) resolve in the deployed skill layout, or bundle them locally.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but heavily padded with redundant enforcement prose (repeated 'MANDATORY', 'CRITICAL', 'YOU MUST', the HARD-GATE block, and duplicate prohibition lists) that could be tightened without loss; it avoids explaining concepts Claude already knows, so it stays above level 1.	2 / 3
Actionability	It provides concrete executable bash (the orchestrate.sh invocation, check-providers.sh, the find-based validation command) and a fully-specified AskUserQuestion payload with specific paths and options, matching 'fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	The five-step sequence is clearly ordered with explicit 'DO NOT PROCEED' gates and a dedicated Step 4 validation gate with error-recovery (show logs, do not substitute), satisfying 'clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	All content lives inline in one ~200-line SKILL.md with no reference files to offload detail (the banner template and parameter blocks could be split out), and the cited paths point to external plugin scripts rather than organized bundle references; sections are well-organized but content that should be separate is inline.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 a capability and includes an explicit trigger, but it relies on generic 'research' language with limited concrete actions and few natural trigger variations, leaving it distinguishable but not strongly distinctive.

Suggestions

Add concrete actions to boost specificity, e.g. '…gathers, cross-checks, and synthesizes findings from multiple sources…'.

Expand trigger terms to natural phrasings users actually say, such as 'investigate', 'compare options', or 'look into'.

Sharpen the niche to reduce conflict risk, e.g. specify multi-source / multi-provider synthesis vs. single-source lookups.

Dimension	Reasoning	Score
Specificity	It names the domain ('research across multiple sources') and an action ('broad synthesis') but does not enumerate multiple concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It states both what ('Thorough research across multiple sources') and an explicit when trigger ('use for complex topics needing broad synthesis'), satisfying the 'clearly answers both what AND when with explicit triggers' anchor; not level 2 because the 'Use when…' clause is present.	3 / 3
Trigger Term Quality	'research', 'complex topics', and 'broad synthesis' are relevant but missing common natural variations a user might say ('investigate', 'look into', 'compare'); this fits 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The 'research' framing is generic and could overlap with other research skills, though the 'complex topics needing broad synthesis' qualifier adds some niche, matching 'somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	9 / 12 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: .claude/skills/skill-deep-research/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.