deep-research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, WHY HOW WHAT papers, 3W literature scan, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 三段式文獻掃描, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題, 심층 연구, 문헌 조사, 체계적 문헌고찰, 메타분석, 사실 확인, 연구 방향을 잡아줘, 연구 주제 정하는 것을 도와줘.

Quality

86%

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

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 is a well-organized, actionable skill with strong workflow sequencing and validation checkpoints and good progressive-disclosure structure. Its main weakness is conciseness: verbose version-notes and opaque internal-coordination jargon inflate the token budget without aiding execution.

Suggestions

Move the #666/#667/#669/#681 'replay-validated artifact' and Material Passport/ARS v3.9.2 routing prose into a dedicated versioned-protocol reference file, keeping only the user-facing rule in SKILL.md.

Consolidate or relocate the dense 'shared/contracts/human_subjects/*' reference rows into a single grouped pointer rather than listing each schema inline.

Trim the per-version prose callouts (v2.4, v3.4.0, v3.5.1, v3.9.2) into the changelog reference, retaining only the current behavioral rule.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but the ~600-line body carries padded version notes and opaque internal-jargon blocks (#666/#667/#669/#681 'replay-validated artifact' lines, Material Passport, ARS v3.9.2 routing prose) that read as changelog leakage Claude does not need.	3 / 5
Actionability	Provides concrete, actionable guidance — a 13-agent table, sequenced orchestration workflow, mode-selection ASCII flow, templates, anti-patterns with correct behavior, and executable env-var flags — with only minor gaps for an instruction-oriented skill.	4 / 5
Workflow Clarity	The 6-phase pipeline is clearly sequenced with three explicit Devil's Advocate CHECKPOINTs (PASS/REVISE), a user-confirmation gate after Phase 1, a 2-loop revision cap, and feedback loops for error recovery — explicit validation checkpoints throughout.	5 / 5
Progressive Disclosure	Good overview structure with extensive one-level-deep reference/template/example tables (all checked reference files exist), though some dense shared-contract rows and full orchestration detail are inlined that could live in referenced files.	4 / 5
	Total	16 / 20 Passed

Description

100%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 comprehensive, concrete, and uses third-person voice with explicit 'what' and 'when' coverage plus tri-lingual natural trigger terms. It is a strong, low-conflict, well-scoped skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (research question formulation, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation) plus 8 distinct modes — comprehensive coverage.	5 / 5
Completeness	Explicitly answers 'what' (universal 13-agent deep research pipeline covering named capabilities) and 'when' via a 'Triggers on:' clause with concrete trigger phrases, satisfying both halves.	5 / 5
Trigger Term Quality	Extensive natural keywords across English, Traditional Chinese, and Korean including synonyms and abbreviations (PRISMA, fact-check, 3W literature scan, 'guide my research', 'help me think through') that users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear academic-deep-research niche with distinct triggers; the body's 'Does NOT Trigger' table routes writing, reviewing, and pipeline work to sibling skills, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (601 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: Imbad0202/academic-research-skills
Path: deep-research/SKILL.md
Commit: 9443623

Reviewed: 4 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.