Template workflow hub

When intent is clear, open the matching child SKILL.md directly. When ambiguous, use the routing table, then load exactly one child skill.

Ambiguous routing

• "start" / "set up" / fresh clone / "does this work" → startup/SKILL.md. Installs deps, runs core pipeline on template_code_project, validates outputs end-to-end.
• Broken refs / "manuscript wrong" — ask whether the failure is pipeline (validate/render) or prose (tokens/registry). Route to manuscript-cross-references, validation-quality, or manuscript-claim-verification. Do not open code-development.
• Example: "refs broken, not sure if pipeline or prose" → clarify stage vs registry; default to cross-refs when [[FIG:]] / labels.yaml mentioned.
• Full health check with no symptom → comprehensive-assessment.
• Skill discovery / "make this repo more agentic" / external agentic or retrieval reference review such as Steward OS, AutoResearch CLI, or LEANN → agentic-use.
• Generic coding homework or unrelated app → do not load template workflow skills.

Routing table

| Symptom or goal | Child skill | | --- | --- | | Fresh clone, "start", "set up the repo", first-time install + validation | startup/SKILL.md | | Research question, literature review, fact check, systematic review | deep-research/SKILL.md | | Draft, outline, revise, format, or disclose AI use in a manuscript | academic-paper/SKILL.md | | Peer review, methodology review, re-review, or calibration | academic-paper-reviewer/SKILL.md | | Research → write → verify → review → revise → finalize | academic-pipeline/SKILL.md | | Methods, methodology, stage contracts, artifact/evidence wiring | methods-orchestration/SKILL.md | | Pipeline stage failed, stuck, or flaky | pipeline-debugging/SKILL.md | | Regenerate-from-clean / determinism / double-run diff | reproducibility-audit/SKILL.md | | Publication-readiness sign-off across tests, evidence, methods, artifacts, and renders | publication-audit/SKILL.md | | Triple-check every manuscript claim; pre-submission | manuscript-claim-verification/SKILL.md | | [[FIG:]] / labels.yaml registry audit | manuscript-cross-references/SKILL.md | | New manuscript + project from research brief | manuscript-creation/SKILL.md | | Literature search corpus synthesis (LLM blocks) | literature-synthesis/SKILL.md | | Full repo audit (tests, docs, manuscript, pipeline) | comprehensive-assessment/SKILL.md | | Skill inventory, agent onboarding, routing hardening, external skill, Steward OS-style operating-model review, AutoResearch CLI measurement patterns, or LEANN semantic-retrieval guidance | agentic-use/SKILL.md | | Validation CLI, gates, markdown/PDF checks | validation-quality/SKILL.md | | New module or algorithm (thin orchestrator) | code-development/SKILL.md | | Tests under no-mocks policy | test-creation/SKILL.md | | End-to-end feature across layers | feature-addition/SKILL.md | | Clean-break refactor with migration | refactoring/SKILL.md | | New infrastructure/* package | infrastructure-module/SKILL.md | | AGENTS.md / README.md for a directory | documentation-creation/SKILL.md |

New project scaffold (one-shot): docs/guides/new-project-one-shot-prompt.md — not a separate skill; link from manuscript-creation when starting from zero.

Conventions (all children)

• Project names: docs/_generated/active_projects.md — never hard-code rotating paths.
• Business logic: infrastructure/ or projects/<name>/src/ only; scripts orchestrate.
• Tests: no mocks; infra ≥60%, project ≥90% unless CI documents an exception.
• Metrics: measure with pytest or cite docs/_generated/COUNTS.md.

Composing a custom workflow

To assemble a custom subset of pipeline stages (discover → fetch → synthesize → write → verify → review → validate → publish) instead of running the whole --pipeline, follow the Workflow Composition Map.

Discovery

These skills are indexed in .cursor/skill_manifest.json (uv run python -m infrastructure.skills write). Human index: README.md.

External design note

This workflow set includes original, template-native adaptations of patterns observed in Imbad0202/academic-research-skills: mode registries, data-access labels, provenance checkpoints, and benchmark disclosure. ARS content is not vendored or copied because ARS is CC-BY-NC-4.0 while this repository is Apache-2.0.

Several ARS ideas are now backed by deterministic infrastructure (code, not prompts), in keeping with the template's "Code Before Prompts" principle:

• Reference-existence verification — infrastructure/reference/verification

resolves each cited DOI/arXiv id/title against Crossref/OpenAlex/arXiv and flags fabricated/mismatched/anachronistic citations. Offline-first with a persistent SQLite cache; live resolution is opt-in. This is the anti-leakage tier-0 gate distilled from the ARS hallucination taxonomy and verification cache. CLI: python -m infrastructure.reference.verification verify <bib>.

• AI-writing fingerprint scan — infrastructure/validation/content/ai_writing.py

scores em-dash density, stock LLM phrasing, and sentence-length burstiness. CLI: python -m infrastructure.validation.cli prose-quality <path>.

These run fully offline in CI; only the optional --live resolution pass touches the network.