deep-research

Read this skill when the user asks for a research report, deep research, industry report, analysis report, whitepaper, or any substantive document deliverable; or when the topic requires multi-source retrieval and cross-validation (competitive analysis, market analysis, industry research, deep dive, landscape survey); or when the user is unsatisfied with the depth of an existing answer. Keyword signals: research, deep research, deep dive, analysis, investigate, report, survey, industry analysis, competitive analysis, market analysis. Trigger when: (1) the user wants to produce a formal report or research document as the deliverable; (2) the topic requires current, verifiable data from multiple sources — news, market analysis, competitive landscape, industry research; (3) the user is unsatisfied with the depth of an existing answer. Skip when a single search or model recall suffices and no document output is needed.

Quality

70%

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 ./backend/super-magic/agents/skills/deep-research/SKILL.md

Quality

Content

50%

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

The body is well-structured and procedurally specific, but token efficiency suffers from full bilingual duplication, and several referenced files (notably deepen-guide.md) are missing or undeclared, weakening navigation and self-sufficiency.

Suggestions

Ship the referenced bundle files (research-workflow.md, report-template.html) and add deepen-guide.md to the References section or stop referencing it.

Replace inline bilingual duplication ( blocks) with a single language or a separate localized file to reclaim the ~2x token overhead.

Inline the key validation/checklist steps for the report phase instead of only deferring them to research-workflow.md, so the core workflow is self-contained.

Dimension	Reasoning	Score
Conciseness	Per-language prose is tight and procedural with no over-explanation of known concepts, but every section is duplicated inline via <!--zh --> Chinese blocks, roughly doubling token cost.	2 / 3
Actionability	Concrete, specific guidance (parallel query angles, ≤3 confirm questions, exactly 3 add-ons, localization, Scenario-B decision tree, sample Q&A card), but it defers the real workflow to external files and references a missing deepen-guide.md.	2 / 3
Workflow Clarity	Steps 1–4 are clearly sequenced with an explicit confirm-before-retrieval gate and a deepen feedback loop, but full validation/checklist detail is deferred to referenced files rather than being self-contained.	2 / 3
Progressive Disclosure	A dedicated, well-signaled one-level-deep References section with per-file conditions, but the referenced files are absent from the bundle and deepen-guide.md is referenced without being declared.	2 / 3
	Total	8 / 12 Passed

Description

90%

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, well-targeted description with excellent trigger-term coverage, explicit when/skip guidance, and a distinct niche. Its only weakness is light emphasis on concrete actions versus deliverable types.

Dimension	Reasoning	Score
Specificity	Names the research/reporting domain and a few actions ('multi-source retrieval and cross-validation', 'produce a formal report'), but mostly enumerates deliverable types and triggers rather than a comprehensive set of concrete action verbs.	2 / 3
Completeness	Explicitly answers both what (formal multi-source cross-validated research deliverable) and when via 'Trigger when: (1)...(2)...(3)...' plus a 'Skip when...' clause; the imperative 'Read this skill when...' mirrors accepted 'Use when...' guidance.	3 / 3
Trigger Term Quality	Broad, natural keyword coverage — 'research, deep research, deep dive, analysis, investigate, report, survey, industry analysis, competitive analysis, market analysis, whitepaper, landscape survey' — matching terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	Clear niche — substantive research reports requiring multi-source retrieval and cross-validation — with distinct triggers and an explicit skip rule, making conflict with simple-search skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/deep-research/SKILL.md
Commit: 41d7ef4

Reviewed: about 13 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.