manuscript-cycle
Skill4 starsChanged 6 months agoMITView on GitHub
End-to-end orchestrator — runs the whole CLAUDE.md research lifecycle for a section or manuscript as one command (outline → ground → draft → verify → review → revise), halting on any gate failure.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- abstractSkill
- citation-auditSkill
- claim-checkSkill
- cover-letterSkill
- gap-finderSkill
- journal-fitSkill
- lit-briefingSkill
- literature-reviewSkill
- lit-ingestSkill
- lit-lintSkill
- methods-reviewSkill
- noteSkill
- outlineSkill
- peer-reviewSkill
- plain-language-summarySkill
- reference-formatSkill
- response-to-reviewersSkill
- retroSkill
- review-resurfaceSkill
- scorecardSkill
- stats-checkSkill
- submission-pipelineSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Read MANUSCRIPT_MAP.md (thesis, contribution, venue, the Structure table) and CLAUDE.project.md / STYLE.md if present.
- Very specific: line 31
If the section's claim/evidence plan is missing from the map, run /outline for it (or dispatch the outline-planner agent).
- Very specific: line 38
Write the smallest passage that makes each point, matching the manuscript's voice (STYLE.md).
- Very specific: line 44
Run /claim-check on the draft: every claim cited / author's-own / common-knowledge.
- Very specific: line 45
GATE: if citation-gate, compile-gate, or /claim-check reports a failure, stop and fix before any review.
- Very specific: line 48
Run /peer-review (dispatches peer-reviewer + integrity-reviewer).
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Manuscript Cycle
Core Rule
Run the Question → Evidence → Draft → Verify → Cite lifecycle end-to-end, and halt at the first gate that fails — never draft past an unresolved citation, an unsupported claim, or a failed compile. This skill orchestrates the kit's existing skills and agents; it does not bypass any of their rules. A clean cycle means: every \cite resolves, every claim is sourced and calibrated, the log compiles, and a simulated reviewer would sign off.
When to Use
Invoke with /manuscript-cycle [section] when:
- Taking a section from outline to review-ready in one pass
- You want the full discipline loop run for you, with the gates enforced
- Running headless (
/manuscript-cycle mode:headless) over a spec for an unattended draft pass
Scope it: /manuscript-cycle introduction works one section; /manuscript-cycle reads the next not-started section from MANUSCRIPT_MAP.md → Structure.
Process
Phase 0 — Load & scope
- Read
MANUSCRIPT_MAP.md(thesis, contribution, venue, the Structure table) andCLAUDE.project.md/STYLE.mdif present. - Pick the target section (argument) and restate it as a claim a reader could dispute (the section's Question).
- Confirm the scope with the author unless
mode:headless(then proceed and report).
Phase 1 — Outline (argument architecture)
- If the section's claim/evidence plan is missing from the map, run
/outlinefor it (or dispatch theoutline-planneragent). Each section states the one claim it establishes, the evidence it needs, and a word budget. - GATE — evidence availability: if the outline flags evidence not in the library (
references.bib/sources// vault), surface it. Run/lit-briefingfor gaps and propose search directions. Do not draft around a citation you intend to "find later." Halt for the author if a load-bearing source is missing (headless: mark the gap and skip that claim).
Phase 2 — Ground
- Pull the supporting evidence for each claim from the vault (
/literature-reviewfor related work; readvault/summaries/for specifics). Confirm each intended\citekey exists inreferences.bib.
Phase 3 — Draft
- Write the smallest passage that makes each point, matching the manuscript's voice (
STYLE.md). Every non-trivial claim carries a real\cite; unknowns get[CITE]/[VALUE — verify]— never a fabrication.
Phase 4 — Verify (the hard gate)
- The hooks run on each edit. Before proceeding, confirm:
- citation-gate passed (no dangling
\cite/\ref) —.hook-state/last_quality_gate.json. - compile-gate clean if a
.logexists. - Run
/claim-checkon the draft: every claim cited / author's-own / common-knowledge; verbs calibrated to the evidence.
- citation-gate passed (no dangling
- GATE: if citation-gate, compile-gate, or
/claim-checkreports a failure, stop and fix before any review. Do not advance with[CITE]placeholders silently embedded — report(sourced / placeholder / unverified).
Phase 5 — Review
- Run
/peer-review(dispatchespeer-reviewer+integrity-reviewer). For numeric/empirical sections also run/stats-check; for methods,/methods-review. - Triage findings: address every Major issue now (re-entering Phase 3–4 as needed); list Minor issues for the author.
Phase 6 — Revise / respond
- Apply the fixes. If this cycle is answering real reviewers, run
/response-to-reviewers(quote → change → location; never claim an unmade change). Log any recurring critique totasks/reviews/.
Phase 7 — Report
- Produce the cycle report (below). In
mode:headless, write it totasks/and stop at the first hard gate rather than asking.
Output Format
# Manuscript Cycle — <section> (<date>)
Thesis: <one line> Stage: <from MANUSCRIPT_MAP>
Phase results
- Outline ......... <ok | evidence gaps: N>
- Ground .......... <sources used: keys>
- Draft ........... <words / budget>
- Verify .......... citation-gate <pass/FAIL> · compile-gate <pass/skip/FAIL> · claim-check (sourced/placeholder/unverified)
- Review .......... Major: N · Minor: N (recommendation)
- Revise .......... <fixes applied / response letter>
HALTED AT: <phase + reason> # if any gate failed
Open for author: <minor issues, evidence gaps, decisions>Pairs With
/outline · /literature-review · /lit-briefing · /claim-check · /stats-check · /methods-review · /peer-review · /response-to-reviewers; gated by citation-gate.sh / compile-gate.sh / stop-gate.sh. It is the research analogue of the code kit's /feature-cycle.
Common Rationalizations (rejected)
- "Draft now, find the citation later." → Phase 1 gate forbids it. Surface the gap.
- "Skip review, it's a small section." → Major issues hide in small sections; Phase 5 runs.
- "The placeholder is fine for now." → Only if reported in the tally; never silently shipped past Phase 4.
Notes
- Headless (
mode:headless): no interactive confirmations — proceed with stated assumptions, halt at the first hard gate, and write the report totasks/. Use for an unattended first-draft pass; a human still reviews before submission. - This skill never relaxes a gate. If a gate is wrong (broken infra), the author sets
SKIP_QUALITY_GATE=1deliberately and records why — the cycle does not bypass it on its own. - Reasoner-tier for outline/review phases, Drafter-tier for the draft phase (
CLAUDE.md → Model Selection).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

