octopus-research

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

Quality

60%

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-research/SKILL.md

Quality

Content

62%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 a strongly sequenced, executable orchestration workflow with real validation gates and error feedback loops, scoring high on workflow clarity and actionability. Its main weaknesses are verbosity from repeated enforcement language and weak progressive disclosure, since large inline blocks could be split into bundle files that do not currently exist.

Suggestions

Collapse the repeated MANDATORY/CRITICAL/PROHIBITED enforcement text into a single contract block; the STEP 3 prohibition list and Error Handling section restate it almost verbatim.

Move the full AskUserQuestion literal and the banner template into referenced bundle files (e.g., references/questions.js, references/banner.txt) so the main flow stays lean.

Add the referenced files (codex-host-adapter.md, skill-security-framing.md) to the bundle under references/ so the one-level-deep navigation is real rather than pointing at external install paths.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose and padded: the enforcement contract is repeated across the HARD-GATE block, the STEP 3 prohibition list, and the Error Handling section, and the full AskUserQuestion literal with every option description is inlined; not a 3 because the redundancy and restated prohibitions go beyond minor tightening.	2 / 5
Actionability	Provides copy-paste-ready bash commands with concrete script paths and an executable verification block; not a 5 because placeholders like "<user's research question>" and ${depth_choice} require substitution and a couple of steps rely on external scripts whose behavior is not shown.	4 / 5
Workflow Clarity	Clear 5-step sequence with explicit BLOCKING gates, a mandatory Step 4 validation gate that fails the run if no synthesis file is found, and a dedicated Error Handling section with feedback loops (show logs, do not fall back); matches the 'explicit validation steps; feedback loops for error recovery' anchor.	5 / 5
Progressive Disclosure	References exist (codex-host-adapter.md, skill-security-framing.md, orchestrate.sh) but no bundle files are present under references/scripts/assets, and the referenced paths point to external install locations rather than a one-level-deep bundle; the full banner literal and AskUserQuestion block are inlined content that could live in separate files.	3 / 5
	Total	14 / 20 Passed

Description

58%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 grammatically in third person with an explicit 'use for' trigger clause, so it answers both what and when. It is somewhat generic, though, lacking concrete action detail and trigger synonyms that would sharpen distinctiveness.

Suggestions

Add concrete actions or deliverables (e.g., 'compares findings, cites sources, produces a synthesis report') to raise specificity.

Expand trigger terms with natural synonyms users say (e.g., 'compare options', 'literature review', 'multi-source summary') to improve trigger coverage.

Tighten the 'when' clause with explicit trigger phrases to reduce overlap with generic research skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('research across multiple sources') and two actions ('research', 'broad synthesis'), but no concrete sub-actions like source types or output formats, matching the '1-2 concrete actions but not comprehensive' anchor; not a 4 because no specific actions beyond the generic research/synthesis verbs.	3 / 5
Completeness	Explicitly states both what ('thorough research across multiple sources', 'broad synthesis') and when ('use for complex topics needing broad synthesis'); not a 5 because the 'when' trigger is fairly general rather than a concrete trigger phrase list.	4 / 5
Trigger Term Quality	Includes natural terms ('research', 'complex topics', 'synthesis') a user might say, but misses common synonyms and concrete triggers; not a 4 because coverage is thin with no variations or file/extension-style triggers.	3 / 5
Distinctiveness Conflict Risk	'Research across multiple sources' is a broad category that could overlap with other research/synthesis skills, though 'multi-source broad synthesis' gives it some niche; not a 4 because the trigger surface is still fairly generic.	3 / 5
	Total	13 / 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-research/SKILL.md
Commit: 805d58c

Reviewed: 1 day 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.