Agent skill
rapid-manuscript-drafter
Draft research manuscripts quickly with structured sections, evidence links, and confidence ceilings.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/design/rapid-manuscript-drafter
SKILL.md
STANDARD OPERATING PROCEDURE
Purpose
- Produce rapid, coherent research manuscript drafts while preserving evidential integrity.
- Enforce constraint clarity (venue, length, style) and explicit ceilings on claims.
- Keep structure-first artifacts ready for iteration and review.
Trigger Conditions
- Positive: first-pass manuscripts, section rewrites, or structured outlines.
- Negative: final camera-ready polishing (use publication skills) or prompt-only edits (
prompt-architect).
Guardrails
- Bucket constraints: HARD (venue format, length, deadlines), SOFT (tone, emphasis), INFERRED (reviewer expectations) with sources.
- Two-pass drafting: outline/structure → evidence and epistemic validation.
- All claims tie to evidence; ceilings reflect evidence type.
Inputs
- Target venue/template, key findings, figures/tables, references.
- Audience and novelty/impact story.
Workflow
- Frame & Constraints: Capture venue rules, deadlines, and required sections; confirm INFERRED reviewer needs.
- Outline Pass: Build section-by-section outline with thesis and contributions.
- Draft Pass: Fill sections with claims linked to evidence, figures, and references; enforce clarity.
- Validation Pass: Check constraints (length/style), evidence coverage, and confidence ceilings; remove overclaims.
- Package: Provide draft, change log, and next edits; store alongside README/examples.
Validation & Quality Gates
- Outline and draft both completed; deltas captured between passes.
- Claims cite evidence and include ceilings.
- Formatting and length conform to venue constraints.
Response Template
**Constraints**
- HARD / SOFT / INFERRED.
**Outline Snapshot**
- ...
**Draft Status**
- Sections completed, evidence links, gaps.
**Risks / Next Edits**
- ...
Confidence: 0.79 (ceiling: inference 0.70) - based on drafted sections and evidence links.
Confidence: 0.79 (ceiling: inference 0.70) - reflects completed passes with cited evidence.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?