AgentStack
SKILL verified MIT Self-run

Food Pipeline

skill-pangenomeai-academic-skills-food-nutrition-food-pipeline · by PangenomeAI

Master orchestrator for the whole food & nutrition research-to-publication workflow. Coordinates the specialist skills — each with its own subagent set — into one governed path: journal selection, research (food-research / deep-research), writing & analysis (food-paper), figures (food-figure), peer review (food-review), revision, and finalization. Use when the user wants the entire process manage…

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-pangenomeai-academic-skills-food-nutrition-food-pipeline

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Food Pipeline? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Food-Pipeline — Master Research-to-Publication Orchestrator

The top-level conductor. It does not do research, writing, or review itself — it routes the project to the specialist skills (each a multi-subagent system), enforces quality gates between stages, and manages the review→revise loop. Original work.

Skills it orchestrates (each brings its own subagent team)

  • journal-selector — target-journal constraints (structure, limits, reference style, figure spec).
  • food-research — literature/evidence synthesis (quick brief / full review / systematic PRISMA + OHAT). Use deep-research instead for an open-ended, source-validated deep dive or a standalone literature review.
  • food-paper — whole-process manuscript system (field → questions → data/stats → figures → argument → draft → polish → self-review).
  • food-figure — submission-grade figures at the journal spec (invoked within food-paper).
  • food-review — multi-reviewer peer-review panel + formatting compliance.

Own subagents

  • intake_router — reads the project's current state and materials, resolves the target journal, picks the entry stage, and assembles the context each downstream skill needs.
  • quality_gate — the checkpoint between stages: verifies the stage's deliverable meets the gate criteria (integrity, journal compliance, evidence sufficiency) and decides proceed / revise / stop, with the author at mandatory gates.

Stages

| Stage | Skill / agent | Deliverable | Gate | |---|---|---|---| | 0 · ROUTE | intake_router + journal-selector | Entry point + journal constraints | — | | 1 · RESEARCH | food-research (or deep-research) | Evidence brief / gap list / (systematic report) | evidence sufficiency | | 2 · WRITE | food-paper | Draft: analysis, figures (food-figure), argument, references | integrity + journal compliance | | 3 · REVIEW | food-review | Panel report + editorial decision + revision checklist | mandatory author decision | | 4 · REVISE | food-paper (revise) | Revised draft + point-by-point response | issues resolved | | 5 · RE-REVIEW | food-review (re-review) | Verification of the revision | accept / one more loop (cap 2) | | 6 · FINALIZE | food-paper (format-convert) + writer | Submission-ready manuscript + checklist (Word/target format) | final compliance |

Workflow

flowchart TD
    A[Project in] --> R[intake_routerstate + materials + journal + entry stage]
    R --> J[journal-selector]
    R --> S1[Stage 1 RESEARCHfood-research / deep-research]
    S1 --> G1{quality_gateevidence sufficient?}
    G1 -- yes --> S2[Stage 2 WRITEfood-paper -> food-figure]
    G1 -- no --> S1
    S2 --> G2{quality_gateintegrity + journal compliance}
    G2 -- pass --> S3[Stage 3 REVIEWfood-review panel]
    G2 -- fail --> S2
    S3 --> G3{{author decisionmandatory gate}}
    G3 -- revise --> S4[Stage 4 REVISEfood-paper revise]
    S4 --> S5[Stage 5 RE-REVIEWfood-review re-review]
    S5 -- issues --> S4
    S5 -- accept --> S6[Stage 6 FINALIZEformat + Word export]
    G3 -- accept --> S6
    S6 --> OUT[Submission-ready manuscript]

Entry points (mid-pipeline)

intake_router detects where to start: a topic/dataset → Stage 1; a full draft → Stage 2 or 3; reviewer comments in hand → Stage 4. It never restarts completed stages unnecessarily.

References (load as needed)

  • references/mode-advisor.mdintake_router uses it to pick entry stage, research flavor, and skills.
  • references/pipeline-state-machine.md — states, transitions, entry points, loop caps.
  • references/quality-gates.md — the per-stage gate criteria quality_gate applies.

Rules

  • Journal first, journal throughout: re-flow references and re-check limits whenever the target journal changes.
  • Gates are real: quality_gate can send a stage back; integrity and review gates cannot be skipped, and the review decision is always the author's.
  • Food-science standards everywhere: n and error type, validated methods, panel details, ethics/food-safety — enforced at every write/review gate.
  • Don't duplicate work: the specialist skills own their subagents; the pipeline sequences and gates them, it does not re-implement them.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.