draft-strategy

# draft-strategy ## Language Rule Follow an explicit target, venue, audience, or source-artifact language first. Otherwise, write strategy artifacts and user-facing output in the conversation language according to `<agent-home>/roles/response-policy.md`. Preserve quotations, code identifiers, citations, paths, and venue-specific terms when translation would reduce precision. ## Parse Arguments Parse `$ARGUMENTS` as follows: - first word, `mode`: `rebuttal | paper | review | report | proposal | presentation` - `--inputs <comma-separated-paths>`: pre-discovered artifact directories, usually `analysis_project/{paper,doc}/...` or `research/{topic}/` - `--output <dir>`: `<artifact-root>/documents/{date}_{name}/` - `--intensity`: derive the `quick | light | standard | thorough | adversarial` verification tier through [CONVENTIONS §1.1](../../core/CONVENTIONS.md#11-verification-rigor-tiers) - remaining text: task description and context ## Pre-Check Verify the expected analysis files under `{output_dir}/analysis/`: - every mode: `material_index.md` - rebuttal: `reviewer_analysis.md` - paper, review, report, proposal, or presentation: `ref_analysis.md` If a required file is missing, report that `autopilot-draft` Step 1 did not complete; do not invent the analysis. ## Mode Routing Select one strategy template from the first argument: | Mode | Strategy focus | |---|---| | `rebuttal` | Meta-review, priority matrix, and reviewer-by-reviewer response | | `paper` | Positioning,...