food-deep-research
starsforks
How to install food-deep-research?
pangenomeai/academic-skills-food-nutrition/food-deep-research
$npx -y skills add PangenomeAI/academic-skills-food-nutrition --skill food-deep-researchGeneral-purpose deep research that produces a fully written, source-validated literature review on any question: scope it, design the method, discover and screen sources by journal ranking, validate every source, extract and verify evidence, synthesize, stress-test, then write an
SKILL.md
| 1 | # Deep-Research — Source-Validated Literature Review Engine |
| 2 | |
| 3 | Answer a hard question properly and hand back a **written, formatted, integrity- |
| 4 | checked literature review** — not just notes. Scope → design → discover → screen |
| 5 | by journal ranking → validate sources → extract & verify evidence → synthesize → |
| 6 | stress-test → write → review-loop → final report. Original work; architecture |
| 7 | informed by open community food-deep-research skills (see the repo README |
| 8 | Acknowledgements). Usable standalone, or as the deep-dive engine called by |
| 9 | `food-research`. |
| 10 | |
| 11 | ## Modes |
| 12 | - **quick brief** — scope → discover → screen (Tier 1) → light synthesis → short sourced answer. Skips the full validation/compile/review loop. |
| 13 | - **full** — the default: the complete 12-subagent pipeline below with the iterate-to-saturation and compile↔review loops, ending in a finished review. |
| 14 | |
| 15 | ## Subagent team (dispatch via the Agent tool) |
| 16 | | # | Subagent | Job | |
| 17 | |---|---|---| |
| 18 | | 1 | `research_scope` | Comprehensive scope brief: background, problem, significance, central + sub-questions, concepts, boundaries, success criteria. | |
| 19 | | 2 | `research_architect` | Methodology blueprint: review type, search strategy, inclusion criteria, analytical framework, reporting standard, stopping criteria. | |
| 20 | | 3 | `investigator` | Pass 1 discover candidate sources; Pass 2 extract evidence **from validated sources only** (parallel per sub-question). | |
| 21 | | 4 | `source_screener` | Prioritize candidates by **journal ranking** (Tier 1 Q1/Q2 + Nature/Science/Cell + other-discipline Q1/Q2; Tier 2 Q3; avoid Tier 4). | |
| 22 | | 5 | `source_verifier` | Validate each prioritized source (existence/DOI, venue legitimacy, retraction, predatory, methodology, COI) → Source Quality Matrix. | |
| 23 | | 6 | `bibliography` | Deduplicate + format references (APA 7.0 default, or target-journal style via `journal-selector`); build the citation map + `.bib/.ris`. | |
| 24 | | 7 | `claim_verifier` | Verify each load-bearing claim against its validated source; classify fact/hypothesis/contested/speculation. | |
| 25 | | 8 | `synthesizer` | Evidence matrix, thematic synthesis, conflict reconciliation, evidence grading, coverage advisory, gap agenda, narrative arc. | |
| 26 | | 9 | `critic` | Devil's advocate on the **synthesis**; loop back to investigate if gaps. | |
| 27 | | 10 | `compiler` | Write & format the **literature-review draft** (APA 7.0 / target journal); cite by key only; no fabrication. | |
| 28 | | 11 | `editor` | Editorial review of the draft (5 weighted dimensions, verdict + prioritized feedback). | |
| 29 | | 12 | `ethics_reviewer` | Integrity/ethics review of the draft (citation integrity, faithful representation, bias, COI, disclosure). | |
| 30 | |
| 31 | ## Workflow |
| 32 | |
| 33 | ```mermaid |
| 34 | flowchart TD |
| 35 | A[research_scope<br/>scope brief] --> B[research_architect<br/>methodology blueprint] |
| 36 | B --> C[investigator Pass 1<br/>discover candidate sources] |
| 37 | C --> D[source_screener<br/>journal-ranking tiers] |
| 38 | D --> E[source_verifier<br/>validate → Source Quality Matrix] |
| 39 | E --> F[bibliography<br/>dedupe + format + citation map] |
| 40 | E --> G[investigator Pass 2<br/>extract evidence from validated sources] |
| 41 | G --> H[claim_verifier<br/>verify claims vs validated sources] |
| 42 | H --> I[synthesizer<br/>matrix, themes, conflicts, grading, gaps] |
| 43 | I --> J[critic<br/>stress-test synthesis] |
| 44 | J -- gaps --> C |
| 45 | J -- sound --> K[compiler<br/>write + format review<br/>APA 7.0 / target journal] |
| 46 | F --> K |
| 47 | K --> L[editor + ethics_reviewer<br/>editorial + integrity review] |
| 48 | L -- minor/major revision --> K |
| 49 | L -- accept --> M[Final literature review] |
| 50 | ``` |
| 51 | |
| 52 | **Two loops:** (1) *evidence loop* — `critic` sends gaps back to `investigator` |
| 53 | (cap ~2–3); (2) *writing loop* — `editor`/`ethics_reviewer` send revisions back |
| 54 | to `compiler` until Accept (cap ~2–3), then deliver. |
| 55 | |
| 56 | ## First move — set up full-text access (onc |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
