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

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

73%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 delivers a well-sequenced, validated workflow with executable commands and feedback loops — its strongest dimension. It loses points on conciseness due to redundant enforcement rhetoric and on actionability due to a placeholder taskId, and it is monolithic with no progressive-disclosure references.

Suggestions

Collapse the repeated HARD-GATE / PROHIBITED / MANDATORY refrains into a single concise contract statement to reduce token cost.

Replace the placeholder taskId: "..." in the TaskUpdate example with guidance on capturing the real task id from TaskCreate's return value.

Fix the duplicated 'Antigravity CLI' banner line (shown twice with different emoji) which is a minor correctness/clarity bug.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete bash commands, but the HARD-GATE block plus repeated 'PROHIBITED'/'MANDATORY'/'NOT optional' refrains are redundant padding that could be tightened.	3 / 5
Actionability	Provides concrete, executable bash (orchestrate.sh probe, check-providers.sh, find SYNTHESIS_FILE) and an AskUserQuestion call; minor gaps such as the placeholder taskId: "..." keep it just below fully copy-paste ready.	4 / 5
Workflow Clarity	Clear five-step sequence with an explicit validation gate (Step 4 verifies the synthesis file) and a dedicated error-handling section with retry guidance; matches the anchor for clear sequence with explicit validation and feedback loops.	5 / 5
Progressive Disclosure	Single self-contained file organized into clearly headed steps; the referenced paths (orchestrate.sh, skill-security-framing.md) are external plugin locations rather than skill bundle files, so structure is good but no deliberate one-level-deep reference split exists.	4 / 5
	Total	16 / 20 Passed

Description

47%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 third-person and answers both what and when, but relies on generic language ('research', 'broad synthesis') with no natural user trigger phrases and high overlap risk. It reads as a broad category rather than a distinctive, concretely-scoped skill.

Suggestions

Add concrete actions the skill performs (e.g., 'runs multi-provider probes via orchestrate.sh, synthesizes findings into a report') to lift specificity.

Include natural trigger phrases users would actually say ('research this topic', 'investigate how X works', 'compare options for Y') to improve trigger term quality.

Sharpen the 'when' clause with explicit trigger conditions to reduce conflict risk with other research skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('research across multiple sources') and gestures at synthesis, but describes no concrete actions beyond generic 'research'; matches the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.	3 / 5
Completeness	States what it does ('Thorough research across multiple sources') and when to use it ('use for complex topics needing broad synthesis'); both what and when are explicit, though the 'when' is somewhat abstract rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	Only generic keywords ('research', 'complex topics', 'broad synthesis'); missing the natural phrases users say ('research this', 'investigate how X works'), which the rubric anchors at score 2.	2 / 5
Distinctiveness Conflict Risk	'Research' is extremely broad with high overlap risk against many research-flavored skills; no distinct niche signals in the description alone.	2 / 5
	Total	11 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-deep-research/SKILL.md
Commit: 6a1fd2b

Reviewed: 3 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.