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

77%

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 ./deep-research/SKILL.md

Quality

Content

62%

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

A well-architected orchestration skill with excellent workflow clarity (phased checkpoints, verdict gates, failure recovery) and good reference organization. It is held back by inline redundancy with the frontmatter triggers, scattered version notes, and a large set of referenced bundle files (agents/templates/examples/scripts) that are not actually bundled.

Suggestions

Remove the inline English/Chinese/Korean trigger-keyword lists from the body — they duplicate the frontmatter description and inflate the token budget.

Consolidate time-sensitive version notes (v2.4, v3.9.2, v3.4.0, v3.5.1, #517) into references/changelog.md so operational sections stay evergreen.

Either bundle the referenced agents/, templates/, examples/, and scripts/ files, or mark them clearly as living in the academic-pipeline/academic-paper sibling skills so dead in-bundle links are eliminated.

Dimension	Reasoning	Score
Conciseness	Mostly efficient structured reference (agent table, mode table, workflow diagram, anti-patterns), but it repeats the frontmatter's full English/Chinese/Korean trigger-keyword lists inline and scatters time-sensitive version chatter (v2.4, v3.9.2, v3.4.0, v3.5.1, #517) through operational content rather than confining it to the changelog — could be tightened.	2 / 3
Actionability	Concrete structure is present (verdict vocabularies PASS/REVISE and ACCEPT/MINOR/MAJOR/REJECT, checkpoint gates, the three-way-scan copy-paste markdown template, per-mode word counts), but per-agent executable detail and several how-to procedures are deferred to reference/agent files, so the body's guidance is incomplete for actual execution.	2 / 3
Workflow Clarity	The 6-phase orchestration is clearly sequenced with explicit CHECKPOINT 1/2/3 gates, PASS/REVISE verdicts, user-confirmation gates ("User confirmation before Phase 2"), a revision-loop cap (max 2), and a Failure Paths table mapping trigger conditions to recovery strategies — full feedback loops for a complex process.	3 / 3
Progressive Disclosure	Organization and signaling are strong — purpose tables map every reference, agent, template, and example to its role and 'Used By', and the bundled references/ directory is complete (18/18 table entries present, one level deep). However 28 of the skill's own bundle files referenced in the body (agents/.md ×13, templates/.md ×6, examples/*.md ×8, scripts/check_pipeline_integrity.py) are entirely absent, so navigation breaks for those paths.	2 / 3
	Total	9 / 12 Passed

Description

92%

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, comprehensive description: concrete capabilities, broad multilingual natural triggers, and an explicit trigger clause that jointly answer 'what' and 'when'. The only real weakness is overlap risk with sibling academic skills on the generic word 'research'.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ("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"). Voice is third-person ("13-agent pipeline for rigorous academic research... Covers...") so no first/second-person penalty applies.	3 / 3
Completeness	Explicitly answers both what ("Universal deep research agent team. 13-agent pipeline... 8 modes... Covers...") and when via a literal "Triggers on:" clause with a keyword list, matching the anchor-3 'Use when...' example.	3 / 3
Trigger Term Quality	Extensive natural-language triggers a user would actually say across English ("research, deep research, literature review, systematic review, meta-analysis, PRISMA, fact-check, guide my research, help me think through"), plus 繁體中文 and 한국어 equivalents — broad coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Has a clear research niche with distinctive terms (PRISMA, meta-analysis, systematic review, fact-check, lit-review), but bare "research"/"deep research" overlap with sibling academic-paper / academic-pipeline / academic-paper-reviewer skills — the body itself carries a "Does NOT Trigger" disambiguation table acknowledging this overlap, so it is not clearly conflict-free.	2 / 3
	Total	11 / 12 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 (562 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: 1 missing	Warning

	Total	13 / 16 Passed

Repository: Imbad0202/academic-research-skills
Path: deep-research/SKILL.md
Commit: f7d9d07

Reviewed: 5 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.