deep-research

Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information.

Quality

65%

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/public/deep-research/SKILL.md

Quality

Content

55%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 skill has an excellent, well-sequenced research workflow with an explicit validation gate, but it is held back by significant verbosity and over-explanation of concepts Claude already understands, plus guidance that is illustrative rather than directly executable.

Suggestions

Cut redundant restatements of the core principle and condense the 4-phase methodology into a tight procedure; remove explanations of what 'identify dimensions' or 'iterative refinement' mean.

Replace illustrative query examples with a compact, reusable template the model can apply directly, and tighten the diversity table to a one-line checklist.

Trim the temporal-awareness section, which largely re-explains how dates work, to a short rule plus one example.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose and padded with content Claude already knows (e.g. defining what 'identify dimensions' means, restating the principle multiple times, and a sprawling 4-phase methodology with redundant checklists and tables) where a leaner procedure would suffice.	2 / 5
Actionability	It offers concrete query-pattern examples and a usable table of information types, but the guidance is example-illustrated hints rather than executable commands or scripts; 'fetch and read' is described rather than scripted.	3 / 5
Workflow Clarity	The 4-phase research process is clearly sequenced, and Phase 4 provides an explicit checklist validation gate with a feedback loop ('If any answer is NO, continue researching') before content generation.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no external bundle files to navigate; for a no-bundle skill under ~200 lines the structure is appropriate, though some content (query patterns, temporal table) could be trimmed rather than split.	4 / 5
	Total	14 / 20 Passed

Description

76%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.

A strong, trigger-rich description that clearly signals when to use the skill and positions it against WebSearch. It loses points on specificity because the capability is described as methodology rather than concrete operations.

Suggestions

Replace 'systematic multi-angle research methodology' with concrete actions, e.g. 'Runs multiple parallel searches, fetches full source content, and synthesizes findings across angles'.

Tighten the 'before content generation tasks' trigger to specific content types to reduce overlap with content-creation skills.

State the deliverable explicitly (e.g. 'Produces a structured research summary with facts, examples, and sources') so 'what' is unambiguous.

Dimension	Reasoning	Score
Specificity	Names the domain (web research) and 1-2 concrete actions ('systematic multi-angle research methodology'), but the actions are abstract methodology rather than concrete operations like 'search', 'fetch', or 'synthesize'.	3 / 5
Completeness	Both 'what' (systematic multi-angle research methodology) and 'when' (trigger phrases plus 'before content generation tasks') are present, but the 'what' is methodological rather than concrete deliverables and could be more explicit.	4 / 5
Trigger Term Quality	Comprehensive coverage of natural user phrasings including 'what is X', 'explain X', 'compare X and Y', 'research X' and explicit instruction to use proactively when online information is needed.	5 / 5
Distinctiveness Conflict Risk	The 'Use this skill instead of WebSearch' framing carves a distinct niche, though 'before content generation tasks' is broad and risks overlap with many content-creation skills.	4 / 5
	Total	16 / 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: bytedance/deer-flow
Path: skills/public/deep-research/SKILL.md
Commit: 2a261d2

Reviewed: about 19 hours 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.