deep-research

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 minutes but produces detailed, cited reports. Costs $2-5 per task.

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 ./skills/deep-research/SKILL.md

Quality

Content

82%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 is highly actionable with comprehensive copy-paste CLI examples and a clear sequenced workflow, well-organized into labeled sections and correctly tied to the real research.py bundle; its main weakness is minor redundancy with the description and the absence of explicit validation/separate reference docs.

Dimension	Reasoning	Score
Conciseness	The body is efficient with no concept-padding Claude already knows, but the 'Cost & Time' table and 'Best Use Cases' section restate figures and use cases already in the description, which are minor instances of over-explanation that could be trimmed — anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands for every common case (query, --format, --stream, --no-wait, --status, --wait, --continue, --list) plus output-format and exit-code guidance, matching anchor 5's 'Fully executable; copy-paste ready... specific examples cover the common cases'.	5 / 5
Workflow Clarity	The numbered Workflow section gives a clear sequence (run query → estimate time → monitor/stream or poll → return results → --continue for follow-ups) with a monitoring checkpoint and an Exit Codes section for error handling, but it lacks an explicit validation step after polling completes, fitting anchor 4 ('most checkpoints present; minor validation gaps').	4 / 5
Progressive Disclosure	The body is well-organized into clearly labeled sections and correctly references the real bundle file scripts/research.py (verified present), but it relies on a single implementation script with no separate reference docs for advanced options, fitting anchor 4 ('good structure; references mostly clear; minor organization gaps') rather than anchor 5's explicit one-level-deep reference pointers.	4 / 5
	Total	17 / 20 Passed

Description

70%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 strong on domain naming, natural trigger terms, and explicit use-case guidance, but its concrete actions are minimal (execute research, produce reports) and the 'when' is framed as application domains rather than user-statement triggers.

Suggestions

Add one or two more concrete actions the skill performs (e.g., 'plans a research strategy, searches and reads sources, synthesizes findings into a cited report') to lift specificity from domain-listing to action-listing.

Reframe the 'Use for:' clause as explicit user-statement triggers (e.g., 'Use when the user asks to research a topic, do a literature review, or run competitive/market analysis') to make the 'when' more concrete and push completeness to anchor 5.

Lead with a more distinctive verb phrase than the generic 'research' to reduce overlap risk with ordinary web-search skills.

Dimension	Reasoning	Score
Specificity	The description clearly names the domain ('Execute autonomous multi-step research using Google Gemini Deep Research Agent') and lists concrete use-case domains (market analysis, due diligence, etc.), but the actual actions the skill performs are limited to 'execute research' and 'produces detailed, cited reports' — only 1-2 concrete actions, matching the anchor-3 example 'Processes PDF files and extracts content' rather than anchor 4's 'several specific actions'.	3 / 5
Completeness	Both 'what' ('Execute autonomous multi-step research... produces detailed, cited reports') and 'when' ('Use for: market analysis...') are present with an explicit 'Use for:' trigger clause, but the 'when' lists application domains rather than concrete user-statement triggers like 'when the user asks for... research', matching anchor 4 ('when could be more explicit or specific') rather than anchor 5.	4 / 5
Trigger Term Quality	It surfaces natural terms users would say — 'market analysis', 'competitive landscaping', 'literature reviews', 'technical research', 'due diligence' — giving good keyword coverage, though it lacks synonyms and a user-facing trigger phrasing, falling just short of anchor 5's 'comprehensive coverage including synonyms'.	4 / 5
Distinctiveness Conflict Risk	The 'Google Gemini Deep Research Agent' niche with specific use cases and cost/time signals is mostly distinct, but the generic word 'research' creates minor overlap risk with general web-search or research skills, fitting anchor 4 ('mostly distinct; minor overlap risk') rather than anchor 5's 'minimal conflict risk'.	4 / 5
	Total	15 / 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: sanjay3290/ai-skills
Path: skills/deep-research/SKILL.md
Commit: 281d88d

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.