[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD9R5GJAHRJSFS0GCRBEBS":3,"skill-same:01M7FD9R5GJAHRJSFS0GCRBEBS":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7FD9R5GJAHRJSFS0GCRBEBS","research-pipeline",null,"Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says \"全流程\", \"full pipeline\", \"从找idea到投稿\", \"end-to-end research\", or wants the complete autonomous research lifecycle.","CZX-LBJ\u002Fdeepseek-science","CZX-LBJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204594689?v=4","01M7FC59WQ9PFXT04MKGJDCFFT","czx","01M7FC59XB2GW0BKWN9JTDBQS7",1,"MIT","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fresearch-pipeline\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: research-pipeline\ndescription: \"Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says \\\"全流程\\\", \\\"full pipeline\\\", \\\"从找idea到投稿\\\", \\\"end-to-end research\\\", or wants the complete autonomous research lifecycle.\"\nargument-hint: \"[research-direction] [— resume \u003Crun_id>]\"\nallowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex, mcp__codex__codex-reply\n---\n\n# Full Research Pipeline: Idea → Experiments → Submission\n\n> ⏱ **External cadence: non-judgmental heartbeat only.** An overnight `\u002Floop` \u002F\n> `CronCreate` heartbeat may wake, detect a **stalled** phase (no progress, dead\n> process, blocked on a freed resource) and **nudge** it forward — it may NEVER\n> decide the work is good (paper good enough, proof holds, claim supported).\n> Every such verdict stays on its own skill's internal cadence and terminates in\n> the cross-model jury. A heartbeat may say \"keep going,\" never \"good enough.\"\n> See\n> [`shared-references\u002Fexternal-cadence.md`](..\u002Fshared-references\u002Fexternal-cadence.md)\n> (overnight-pipeline rule + stall detection & forced structural pivot). At heartbeat\n> startup, touch the run state first each tick and register this run with the watchdog\n> `loop` type (so a silent death surfaces as STALE); unregister on completion. The\n> watchdog only detects — it never acquits. Each tick also record the new-finding count\n> via the `iteration_log.py` helper (resolve through the canonical\n> `.aris\u002Ftools → tools → $ARIS_REPO\u002Ftools → $ARIS_REPO\u002Ftools via ~\u002F.aris\u002Frepo`\n> chain, integration-contract §2; warn-and-skip if unresolved):\n> `python3 \"$ITER_LOG\" note \u003Croot> \u003Crun_id> \u003Cphase> \u003Cn>`. On the returned\n> `pivot=structural` (stale ≥ 2) the nudge must change a STRUCTURAL constraint and pick an\n> untried direction; on `pivot=human` (stale ≥ 4) flag for attention. Counting only —\n> never a quality verdict.\n\nEnd-to-end autonomous research workflow for: **$ARGUMENTS**\n\n## Optional formal proof route\n\nBefore creating an experimental run, route theorem-centered requests for Lean\nto [`\u002Flean-formalize`](..\u002Flean-formalize\u002FSKILL.md) and report its actual proof\nresult. Run the experimental stages below when the task includes empirical\nresearch. In a mixed project, use Lean for a user-requested formal proof or a\nspecific mathematical obligation whose formal verification would materially\nhelp; return its checked scope and remaining obligations to the research summary\nand applicable proof audit. Ordinary mathematics stays in the existing theory\nskills. Difficulty alone does not make Lean mandatory, and a formal sublemma\ndoes not establish an empirical claim.\n\n## Constants\n\n- **AUTO_PROCEED = true** — When `true`, every selection checkpoint is informational: report the choice and continue in the same turn. When `false`, ask for explicit user confirmation and end the turn at the checkpoint.\n- **ARXIV_DOWNLOAD = false** — When `true`, `\u002Fresearch-lit` downloads the top relevant arXiv PDFs during literature survey. When `false` (default), only fetches metadata via arXiv API. Passed through to `\u002Fidea-discovery` → `\u002Fresearch-lit`.\n- **HUMAN_CHECKPOINT = false** — When `true`, the auto-review loops (Stage 3) pause after each round's review to let you see the score and provide custom modification instructions before fixes are implemented. When `false` (default), loops run fully autonomously. Passed through to `\u002Fauto-review-loop`.\n- **REVIEWER_DIFFICULTY = medium** — How adversarial the reviewer is. `medium` (default): standard MCP review. `hard`: adds reviewer memory + debate protocol. `nightmare`: GPT reads repo directly via `codex exec` + memory + debate. Passed through to `\u002Fauto-review-loop`.\n- **CODE_REVIEW = true** — GPT-6-Astra xhigh reviews experiment code before deployment. Catches logic bugs before wasting GPU hours. Set `false` to skip. Passed through to `\u002Fexperiment-bridge`.\n- **BASE_REPO = false** — GitHub repo URL to use as base codebase. When set, `\u002Fexperiment-bridge` clones the repo first and implements experiments on top of it. When `false` (default), writes code from scratch or reuses existing project files. Passed through to `\u002Fexperiment-bridge`.\n- **COMPACT = false** — When `true`, generates compact summary files for short-context models and session recovery. Passed through to `\u002Fidea-discovery` and `\u002Fexperiment-bridge`.\n- **AUTO_WRITE = false** — When `true`, automatically invoke Workflow 3 (`\u002Fpaper-writing`) after Stage 4. `VENUE` is needed only when Stage 5 begins — a missing venue defers paper writing; it never blocks Stages 1-4. When `false` (default), Stage 4 generates `NARRATIVE_REPORT.md` and stops — user invokes `\u002Fpaper-writing` manually.\n- **VENUE = (unset)** — Target venue for paper writing; bound only when Stage 5 begins. Options: `ICLR`, `NeurIPS`, `ICML`, `CVPR`, `ACL`, `AAAI`, `ACM`, `IEEE_CONF`, `IEEE_JOURNAL`. No default: a missing venue defers paper writing — it never blocks Stages 1-4 and is never guessed.\n- **RENDER_HTML = true** — When `true` (default), auto-render `NARRATIVE_REPORT.md` to HTML at Stage 4 completion via `\u002Frender-html`. Uses `--no-review` (this is an internal handoff doc to `\u002Fpaper-writing`, not a reviewer-facing final artifact — the upstream Stage 3 auto-review loop already cross-model-reviewed the claims). Set `false` to skip, or pass `— render html: false`. **Non-blocking**: if `\u002Frender-html` fails or Codex MCP is unavailable, log the failure and continue — the HTML view is a nice-to-have, not a Stage 4 prerequisite.\n\n- **RESUMABLE = true** — When `true` (default), the pipeline records per-stage state to `.aris\u002Fruns\u002F\u003Crun_id>.json` so a crashed\u002Finterrupted run can resume via `\u002Fresearch-pipeline — resume \u003Crun_id>` instead of restarting. Stage status splits `done` (executor finished writing) from `accepted` (the stage's cross-model gate \u002F deterministic verifier passed); resume re-validates any `done`-but-unaccepted stage. See `shared-references\u002Fresumable-runs.md`.\n\n> 💡 Override via argument, e.g., `\u002Fresearch-pipeline \"topic\" — AUTO_PROCEED: false, human checkpoint: true, difficulty: nightmare, code review: false, base repo: https:\u002F\u002Fgithub.com\u002Forg\u002Fproject, auto_write: true, venue: NeurIPS`.\n\n## Checkpoint execution rule\n\nResolve `AUTO_PROCEED` once from `$ARGUMENTS` before Stage 1 and pass that\nresolved value to nested workflows.\n\n- **`AUTO_PROCEED=true` is non-blocking.** A checkpoint is a progress update,\n  not a question. State the result and the automatically selected next action,\n  then continue executing in the **same turn**. Do not ask for confirmation,\n  request user input, sleep, wait for silence, or end the turn at a checkpoint.\n- **`AUTO_PROCEED=false` is blocking.** Present the options, ask the user, and\n  end the turn. Resume only after an explicit reply.\n\nNever implement auto-proceed as “ask, then continue if there is no response.”\nOnce a turn ends, silence cannot resume the pipeline. The user can still\ninterrupt a non-blocking run at any time.\n\nThis rule governs only `AUTO_PROCEED`-controlled selection checkpoints. If the\nuser explicitly enables a Feishu **interactive** gate, that external approval\nor reply is an intentional blocking exception; wait for that user-controlled\ngate rather than treating it as a silence timeout. Feishu off\u002Fpush-only modes\nremain non-blocking under `AUTO_PROCEED=true`.\n\n## Overview\n\nThis skill chains the entire research lifecycle into a single pipeline:\n\n```\n\u002Fidea-discovery → \u002Fexperiment-bridge → \u002Fauto-review-loop → \u002Fpaper-writing (optional)\n├── Workflow 1 ──┤├── Workflow 1.5 ──┤├── Workflow 2 ───┤ ├── Workflow 3 ──┤\n```\n\nIt orchestrates up to four major workflows in sequence. Workflow 3 (paper writing) is optional and controlled by `AUTO_WRITE`.\n\n## Resumable runs (`— resume \u003Crun_id>`)\n\nThis pipeline is long and can fail mid-run; it tracks per-stage state via\n`run_state.py` so you can resume instead of restarting (see\n[`shared-references\u002Fresumable-runs.md`](..\u002Fshared-references\u002Fresumable-runs.md)).\nSkip this whole section if `RESUMABLE = false`.\n\nResolve the helper via the canonical chain (integration-contract §2):\n`.aris\u002Ftools\u002Frun_state.py` → `tools\u002Frun_state.py` → `$ARIS_REPO\u002Ftools\u002Frun_state.py`\n→ `$ARIS_REPO\u002Ftools\u002Frun_state.py` via `~\u002F.aris\u002Frepo`\n(warn-and-skip if unresolved — never block the pipeline).\n\n**Phases**, in order: `idea-discovery, experiment-bridge, auto-review-loop, summary, paper-writing`.\n\n- **At start:** if `— resume \u003Crun_id>` was passed, run\n  `run_state.py resume \u003Croot> \u003Crun_id>` — it prints the first non-`accepted`\n  phase; **begin the pipeline at that stage** (re-run a `running`\u002F`failed` stage;\n  **re-audit** a `done`-but-unaccepted stage). Otherwise derive `\u003Crun_id>` from\n  the direction slug + date and `run_state.py start \u003Croot> \u003Crun_id> --phases\n  \"idea-discovery,experiment-bridge,auto-review-loop,summary,paper-writing\"`.\n- **Per stage:** `set \u003Crun_id> \u003Cphase> running` on entry; `set \u003Crun_id> \u003Cphase>\n  done --artifact \u003Cpath>` once the stage's artifact is written.\n- **Mark `accepted` ONLY after the stage's gate passes** — never on the executor's\n  own say-so (`run_state.py accept` requires a recorded verdict id + reviewer):\n\n  | phase | what sets `accepted` | record as reviewer |\n  |-------|----------------------|--------------------|\n  | `idea-discovery` | Gate 1 cross-model jury \u002F novelty-check passed | `codex-gpt-6-astra` + thread id |\n  | `experiment-bridge` | experiments actually ran (jobs completed) — deterministic | `deterministic:experiment-bridge` |\n  | `auto-review-loop` | the loop hit its positive STOP (`score>=6 AND verdict∈{ready,almost}` — codex's verdict) | `codex-gpt-6-astra` + final review trace id |\n  | `summary` | `NARRATIVE_REPORT.md` written (+ rendered if `RENDER_HTML`) — deterministic | `deterministic:summary` |\n  | `paper-writing` | submission audits passed (`verify_paper_audits.sh` exit 0) — deterministic | `deterministic:verify_paper_audits.sh` |\n\n**If `AUTO_WRITE = false`** (default), `paper-writing` is not part of this run:\nafter `summary` is accepted, `set \u003Crun_id> paper-writing skipped` so `resume`\nreports COMPLETE instead of pointing forever at a pending stage. Record each\n`accept` `verdict_id` as a **durable handle** — the codex thread\u002Ftrace id, or the\npath\u002Fsha of the deterministic verifier's report (e.g. the `verify_paper_audits.sh`\noutput JSON) — not just the reviewer label.\n\nA stage left `done` (gate failed\u002Fambiguous, or the run crashed before the gate)\nis re-validated on the next resume — the acceptance obligation is never skipped.\n\n## Overnight heartbeat: stall detection → forced structural pivot\n\nOnly when an unattended heartbeat is driving this run (overnight `\u002Floop` \u002F\n`CronCreate`). Skip otherwise. Doctrine + rationale:\n[`shared-references\u002Fexternal-cadence.md`](..\u002Fshared-references\u002Fexternal-cadence.md)\n→ \"Stall detection & forced structural pivot\". This is a Type-A signal — it counts\nfindings and changes *direction*, never *judges quality*.\n\nResolve the helper via the canonical chain (integration-contract §2), warn-and-skip\nif unresolved (never block the run):\n```bash\nITER_LOG=\".aris\u002Ftools\u002Fiteration_log.py\"\n[ -f \"$ITER_LOG\" ] || ITER_LOG=\"tools\u002Fiteration_log.py\"\n[ -f \"$ITER_LOG\" ] || ITER_LOG=\"${ARIS_REPO:-}\u002Ftools\u002Fiteration_log.py\"\n[ -f \"$ITER_LOG\" ] || { [ -z \"${ARIS_REPO:-}\" ] && [ -f \"$HOME\u002F.aris\u002Frepo\" ] && ARIS_REPO=\"$(cat \"$HOME\u002F.aris\u002Frepo\" 2>\u002Fdev\u002Fnull)\"; } || true\n[ -f \"$ITER_LOG\" ] || ITER_LOG=\"${ARIS_REPO:-}\u002Ftools\u002Fiteration_log.py\"\n[ -f \"$ITER_LOG\" ] || { echo \"WARN: iteration_log.py not resolved; skipping stall detection\" >&2; ITER_LOG=\"\"; }\n```\nThen, **each heartbeat tick**, record how many concrete new findings the current\nstage produced and read the returned `pivot`:\n```bash\n[ -n \"$ITER_LOG\" ] && python3 \"$ITER_LOG\" note \"$ROOT\" \"$RUN_ID\" \"$STAGE\" \"$N_NEW_FINDINGS\"\n# → {\"stale_count\": N, \"pivot\": \"none|structural|human\"}\n```\nAct on `pivot`:\n- `none` — keep going.\n- `structural` (stale ≥ 2) — the next nudge must change a **structural constraint**\n  (frame \u002F objective \u002F data \u002F representation), not a tactical parameter, and pick a\n  direction different from every one already tried. Record the chosen frame so future\n  ticks can avoid it: `python3 \"$ITER_LOG\" note \"$ROOT\" \"$RUN_ID\" \"$STAGE\" 0 --direction \"\u003Cthe new frame>\"`.\n- `human` (stale ≥ 4) — stop nudging blindly; flag for human attention (escalate, do\n  not silently abandon).\n\nThe heartbeat may say \"keep going \u002F change direction,\" never \"good enough\" — every\nquality verdict still terminates in the cross-model jury (`acceptance-gate.md`).\n\n## Pipeline\n\n### Stage 1: Idea Discovery (Workflow 1)\n\nIf `RESEARCH_BRIEF.md` exists in the project root, it will be automatically loaded as detailed context (replaces one-line prompt). See `templates\u002FRESEARCH_BRIEF_TEMPLATE.md`.\n\nInvoke the idea discovery pipeline:\n\n```\n\u002Fidea-discovery \"$ARGUMENTS\" — AUTO_PROCEED: $AUTO_PROCEED\n```\n\nThis internally runs: `\u002Fresearch-lit` → `\u002Fidea-creator` → `\u002Fnovelty-check` → `\u002Fresearch-review`\n\n**Output:** `idea-stage\u002FIDEA_REPORT.md` with ranked, validated, pilot-tested ideas.\n\n**🚦 Gate 1 — Idea Selection:**\n\nAfter `idea-stage\u002FIDEA_REPORT.md` is generated, present the top ideas.\n\n**If `AUTO_PROCEED=true` (non-blocking):** report the selection and continue\nimmediately in the same turn. Do not phrase the update as a question:\n\n```\n📋 Idea Discovery complete. Top ideas:\n\n1. [Idea 1 title] — Pilot: POSITIVE (+X%), Novelty: CONFIRMED\n2. [Idea 2 title] — Pilot: WEAK POSITIVE (+Y%), Novelty: CONFIRMED\n3. [Idea 3 title] — Pilot: NEGATIVE, eliminated\n\nAUTO_PROCEED: selected Idea 1 — [title]. Continuing to Stage 2.\n```\n\n**If `AUTO_PROCEED=false` (blocking):** present the same ranking, ask\n`Recommended: Idea 1. Shall I proceed with implementation?`, then end the turn.\nThe user may:\n- **Approve the idea** → proceed to Stage 2. `\u002Fexperiment-bridge` reads `refine-logs\u002FEXPERIMENT_PLAN.md` already generated by `\u002Fidea-discovery`.\n- **Request changes** (e.g., \"combine Idea 1 and 3\", \"focus more on X\") → update the idea prompt with user feedback, re-run `\u002Fidea-discovery` with refined constraints, and present again.\n- **Reject all ideas** → collect feedback on what's missing, re-run Stage 1 with adjusted research direction. Repeat until the user commits to an idea.\n- **Stop here** → save current state to `idea-stage\u002FIDEA_REPORT.md` for future reference.\n\n> ⚠️ **This gate waits for user confirmation when AUTO_PROCEED=false.** When `true`, it auto-proceeds after presenting results. The rest of the pipeline (Stages 2-3) is expensive (GPU time + multiple review rounds), so set `AUTO_PROCEED=false` if you want a final review checkpoint before committing GPU resources.\n\n### Stage 2: Experiment Bridge (Workflow 1.5)\n\nOnce the idea is selected (automatically or by the user), delegate implementation and deployment to `\u002Fexperiment-bridge`:\n\n```\n\u002Fexperiment-bridge \"$CHOSEN_IDEA_TITLE\" — code review: $CODE_REVIEW, base repo: $BASE_REPO, compact: $COMPACT\n```\n\n> 💡 **Queue routing is automatic**: `\u002Fexperiment-bridge` Phase 4 routes each milestone by job count — ≤5 jobs → `\u002Frun-experiment`, ≥10 jobs or teacher→student phase dependencies → `\u002Fexperiment-queue` (with OOM retry, wave gating, crash-safe state). No manual override is needed.\n\n**What this does (fully autonomous):**\n1. Parses `refine-logs\u002FEXPERIMENT_PLAN.md` — extracts milestones, run order, compute budget\n2. Implements experiment code — extends pilot to full scale, follows existing codebase conventions\n3. **Cross-model code review** — GPT-6-Astra xhigh reviews the implementation for logic bugs, incorrect metrics, and ground-truth misuse before any GPU time is spent\n4. **Sanity check** — runs the smallest experiment first to verify the environment; auto-debugs failures (up to 3 attempts, with `\u002Fcodex:rescue` fallback)\n5. Deploys full experiments — auto-routes by job count (≤5 → `\u002Frun-experiment`, ≥10 → `\u002Fexperiment-queue` with OOM retry, wave gating, crash-safe state)\n6. Collects initial results — parses outputs, updates `refine-logs\u002FEXPERIMENT_TRACKER.md`, runs `\u002Ftraining-check` if W&B is configured\n7. Auto-plans ablations via `\u002Fablation-planner` if main results are positive\n\n**Output:**\n- `refine-logs\u002FEXPERIMENT_RESULTS.md` — structured results by milestone\n- `refine-logs\u002FEXPERIMENT_TRACKER.md` — updated run-by-run status\n- `EXPERIMENT_LOG.md` (when `COMPACT=true`) — session-recovery-friendly log\n\n**Monitor progress** (while experiments run):\n\n```\n\u002Fmonitor-experiment [server]\n```\n\nWait for `\u002Fexperiment-bridge` to complete and report its handoff summary before proceeding.\n\n### Stage 3: Auto Review Loop (Workflow 2)\n\nOnce initial results are in, start the autonomous improvement loop:\n\n```\n\u002Fauto-review-loop \"$ARGUMENTS — [chosen idea title], difficulty: $REVIEWER_DIFFICULTY\"\n```\n\n**What this does (up to 4 rounds):**\n1. GPT-6-Astra xhigh reviews the work (score, weaknesses, minimum fixes)\n2. Claude Code implements fixes (code changes, new experiments, reframing)\n3. Deploy fixes, collect new results\n4. Re-review → repeat until (score ≥ 6\u002F10 AND verdict ∈ {ready, almost}) or 4 rounds reached\n\n**Output:** `review-stage\u002FAUTO_REVIEW.md` with full review history and final assessment.\n\n### Stage 4: Research Summary & Writing Handoff\n\nAfter the auto-review loop completes, prepare the handoff for paper writing.\n\n**Step 1:** Write a final research status report (same as before).\n\n**Step 2:** Generate `NARRATIVE_REPORT.md` from:\n- `IDEA_REPORT.md` (chosen idea, hypothesis, novelty justification)\n- Implementation details from the repo\n- Experiment configs and final results\n- `AUTO_REVIEW.md` (review history, weaknesses fixed, remaining limitations)\n\nThe narrative report must contain:\n- Problem statement and core claim\n- Method summary\n- Key quantitative results with evidence for each claim\n- Figure\u002Ftable inventory (which exist, which need manual creation)\n- Limitations and remaining follow-up items\n\n**Output:** `NARRATIVE_REPORT.md` + research pipeline report.\n\n```markdown\n# Research Pipeline Report\n\n**Direction**: $ARGUMENTS\n**Chosen Idea**: [title]\n**Date**: [start] → [end]\n**Pipeline**: idea-discovery → experiment-bridge → auto-review-loop\n\n## Journey Summary\n- Ideas generated: X → filtered to Y → piloted Z → chose 1\n- Implementation: [brief description of what was built]\n- Experiments: [number of GPU experiments, total compute time]\n- Review rounds: N\u002F4, final score: X\u002F10\n\n## Writing Handoff\n- NARRATIVE_REPORT.md: ✅ generated\n- Venue: [VENUE or \"not set — run \u002Fpaper-writing manually\"]\n- Manual figures needed: [list or \"none\"]\n\n## Remaining TODOs (if any)\n- [items flagged by reviewer that weren't addressed]\n```\n\n### Stage 5: Paper Writing (Workflow 3 — Optional)\n\n**Skip this stage if `AUTO_WRITE=false` (default).** Present the `\u002Fpaper-writing` command for manual use:\n\n```\n📝 Research complete. To write the paper:\n\u002Fpaper-writing \"NARRATIVE_REPORT.md\" — venue: \u003CVENUE>, AUTO_PROCEED: $AUTO_PROCEED\n```\n\n**If `AUTO_WRITE=true`:**\n\n🚦 **Gate 2 — Writing Checkpoint:**\n\n```\n📝 Research pipeline complete. Ready for Workflow 3.\n\n- Venue: [VENUE]\n- Input: NARRATIVE_REPORT.md\n- Manual figures required: [list or none]\n- Next step: \u002Fpaper-writing \"NARRATIVE_REPORT.md\" — venue: [VENUE], AUTO_PROCEED: $AUTO_PROCEED\n\nProceeding with paper writing...\n```\n\nChecks before proceeding (venue binds HERE — Stages 1-4 are venue-independent):\n- If `VENUE` is missing: with `AUTO_PROCEED=false`, ask now. With\n  `AUTO_PROCEED=true`, do not guess and do not wait — stamp\n  \"VENUE NOT SPECIFIED — paper writing deferred\" in the report and checkpoint,\n  leave the paper-writing phase pending, and finish the run cleanly for a later\n  resume. Never silently pick a venue.\n- If manual figures are required: with `AUTO_PROCEED=false`, pause and list\n  them. With `AUTO_PROCEED=true`, record \"paper writing deferred (manual\n  figures: \u003Clist>)\" and finish cleanly the same way.\n\nThen invoke:\n\n```\n\u002Fpaper-writing \"NARRATIVE_REPORT.md\" — venue: $VENUE, AUTO_PROCEED: $AUTO_PROCEED\n```\n\nPass the resolved `AUTO_PROCEED` explicitly so Workflow 3 cannot silently\nfall back to its own default mode.\n\nThis delegates to Workflow 3 which handles its own phases:\n`\u002Fpaper-plan → \u002Fpaper-figure → \u002Fpaper-write → \u002Fpaper-compile → \u002Fauto-paper-improvement-loop`\n\nWhen Workflow 3 finishes, update the pipeline report with:\n- Paper writing completion status\n- Final PDF path (`paper\u002Fmain.pdf`)\n- Improvement scores (round 0 → round N)\n- Remaining issues\n\n**Output:** `paper\u002F` directory with LaTeX source, compiled PDF, and `PAPER_IMPROVEMENT_LOG.md`.\n\n## Render HTML view (auto, when `RENDER_HTML = true`)\n\nAfter Stage 4 finalizes `NARRATIVE_REPORT.md` (before paper writing branches), invoke `\u002Frender-html` on the narrative report:\n\n```\n\u002Frender-html \"NARRATIVE_REPORT.md\" --no-review\n```\n\n`--no-review` is intentional: this is an internal handoff doc, not reviewer-facing — the claims it summarizes were already cross-model-reviewed in Stage 3's `\u002Fauto-review-loop`. Output: `NARRATIVE_REPORT.html` next to the MD, with embedded source SHA256.\n\n**Non-blocking**: if `\u002Frender-html` fails (helper missing, file write error, etc.), log the failure and continue Stage 4 — the HTML view is a convenience artifact, not a pipeline prerequisite.\n\nSkip this step if `RENDER_HTML = false`.\n\n## Output Protocols\n\n> Follow these shared protocols for all output files:\n> - **[Output Versioning Protocol](..\u002Fshared-references\u002Foutput-versioning.md)** — write timestamped file first, then copy to fixed name\n> - **[Output Manifest Protocol](..\u002Fshared-references\u002Foutput-manifest.md)** — log every output to MANIFEST.md\n> - **[Output Language Protocol](..\u002Fshared-references\u002Foutput-language.md)** — respect the project's language setting\n\n## Key Rules\n\n- **Large file handling**: If the Write tool fails due to file size, immediately retry using Bash (`cat \u003C\u003C 'EOF' > file`) to write in chunks. Do NOT ask the user for permission — just do it silently.\n\n- **The Stage 1 checkpoint is controlled by AUTO_PROCEED.** When `false`, do not proceed without user confirmation. When `true`, report the top selection and continue in the same turn without asking or waiting.\n- **Stages 2-3 can run autonomously** once the idea is selected. This is the \"sleep and wake up to results\" part.\n- **If Stage 3 ends at round 4 without positive assessment**, stop and report remaining issues. Do not loop forever.\n- **Budget awareness**: Track total GPU-hours across the pipeline. Flag if approaching user-defined limits.\n- **Documentation**: Every stage updates its own output file. The full history should be self-contained.\n- **Fail gracefully**: If any stage fails (no good ideas, experiments crash, review loop stuck), report clearly and suggest alternatives rather than forcing forward.\n\n## Typical Timeline\n\n| Stage | Duration | Can sleep? |\n|-------|----------|------------|\n| 1. Idea Discovery | 30-60 min | Yes if AUTO_PROCEED=true |\n| 2. Experiment Bridge | 30-120 min (implement + review + deploy + collect) | Yes ✅ |\n| 3. Auto Review | 1-4 hours (depends on experiments) | Yes ✅ |\n\n**Sweet spot**: Run Stage 1 in the evening, launch Stage 2-3 before bed, wake up to a reviewed paper.\n","# Full Research Pipeline: Idea → Experiments → Submission\n\n> ⏱ **External cadence: non-judgmental heartbeat only.** An overnight `\u002Floop` \u002F\n> `CronCreate` heartbeat may wake, detect a **stalled** phase (no progress, dead\n> process, blocked on a freed resource) and **nudge** it forward — it may NEVER\n> decide the work is good (paper good enough, proof holds, claim supported).\n> Every such verdict stays on its own skill's internal cadence and terminates in\n> the cross-model jury. A heartbeat may say \"keep going,\" never \"good enough.\"\n> See\n> [`shared-references\u002Fexternal-cadence.md`](..\u002Fshared-references\u002Fexternal-cadence.md)\n> (overnight-pipeline rule + stall detection & forced structural pivot). At heartbeat\n> startup, touch the run state first each tick and register this run with the watchdog\n> `loop` type (so a silent death surfaces as STALE); unregister on completion. The\n> watchdog only detects — it never acquits. Each tick also record the new-finding count\n> via the `iteration_log.py` helper (resolve through the canonical\n> `.aris\u002Ftools → tools → $ARIS_REPO\u002Ftools → $ARIS_REPO\u002Ftools via ~\u002F.aris\u002Frepo`\n> chain, integration-contract §2; warn-and-skip if unresolved):\n> `python3 \"$ITER_LOG\" note \u003Croot> \u003Crun_id> \u003Cphase> \u003Cn>`. On the returned\n> `pivot=structural` (stale ≥ 2) the nudge must change a STRUCTURAL constraint and pick an\n> untried direction; on `pivot=human` (stale ≥ 4) flag for attention. Counting only —\n> never a quality verdict.\n\nEnd-to-end autonomous research workflow for: **$ARGUMENTS**\n\n## Optional formal proof route\n\nBefore creating an experimental run, route theorem-centered requests for Lean\nto [`\u002Flean-formalize`](..\u002Flean-formalize\u002FSKILL.md) and report its actual proof\nresult. Run the experimental stages below when the task includes empirical\nresearch. In a mixed project, use Lean for a user-requested formal proof or a\nspecific mathematical obligation whose formal verification would materially\nhelp; return its checked scope and remaining obligations to the research summary\nand applicable proof audit. Ordinary mathematics stays in the existing theory\nskills. Difficulty alone does not make Lean mandatory, and a formal sublemma\ndoes not establish an empirical claim.\n\n## Constants\n\n- **AUTO_PROCEED = true** — When `true`, every selection checkpoint is informational: report the choice and continue in the same turn. When `false`, ask for explicit user confirmation and end the turn at the checkpoint.\n- **ARXIV_DOWNLOAD = false** — When `true`, `\u002Fresearch-lit` downloads the top relevant arXiv PDFs during literature survey. When `false` (default), only fetches metadata via arXiv API. Passed through to `\u002Fidea-discovery` → `\u002Fresearch-lit`.\n- **HUMAN_CHECKPOINT = false** — When `true`, the auto-review loops (Stage 3) pause after each round's review to let you see the score and provide custom modification instructions before fixes are implemented. When `false` (default), loops run fully autonomously. Passed through to `\u002Fauto-review-loop`.\n- **REVIEWER_DIFFICULTY = medium** — How adversarial the reviewer is. `medium` (default): standard MCP review. `hard`: adds reviewer memory + debate protocol. `nightmare`: GPT reads repo directly via `codex exec` + memory + debate. Passed through to `\u002Fauto-review-loop`.\n- **CODE_REVIEW = true** — GPT-6-Astra xhigh reviews experiment code before deployment. Catches logic bugs before wasting GPU hours. Set `false` to skip. Passed through to `\u002Fexperiment-bridge`.\n- **BASE_REPO = false** — GitHub repo URL to use as base codebase. When set, `\u002Fexperiment-bridge` clones the repo first and implements experiments on top of it. When `false` (default), writes code from scratch or reuses existing project files. Passed through to `\u002Fexperiment-bridge`.\n- **COMPACT = false** — When `true`, generates compact summary files for short-context models and session recovery. Passed through to `\u002Fidea-discovery` and `\u002Fexperiment-bridge`.\n- **AUTO_WRITE = false** — When `true`, automatically invoke Workflow 3 (`\u002Fpaper-writing`) after Stage 4. `VENUE` is needed only when Stage 5 begins — a missing venue defers paper writing; it never blocks Stages 1-4. When `false` (default), Stage 4 generates `NARRATIVE_REPORT.md` and stops — user invokes `\u002Fpaper-writing` manually.\n- **VENUE = (unset)** — Target venue for paper writing; bound only when Stage 5 begins. Options: `ICLR`, `NeurIPS`, `ICML`, `CVPR`, `ACL`, `AAAI`, `ACM`, `IEEE_CONF`, `IEEE_JOURNAL`. No default: a missing venue defers paper writing — it never blocks Stages 1-4 and is never guessed.\n- **RENDER_HTML = true** — When `true` (default), auto-render `NARRATIVE_REPORT.md` to HTML at Stage 4 completion via `\u002Frender-html`. Uses `--no-review` (this is an internal handoff doc to `\u002Fpaper-writing`, not a reviewer-facing final artifact — the upstream Stage 3 auto-review loop already cross-model-reviewed the claims). Set `false` to skip, or pass `— render html: false`. **Non-blocking**: if `\u002Frender-html` fails or Codex MCP is unavailable, log the failure and continue — the HTML view is a nice-to-have, not a Stage 4 prerequisite.\n\n- **RESUMABLE = true** — When `true` (default), the pipeline records per-stage state to `.aris\u002Fruns\u002F\u003Crun_id>.json` so a crashed\u002Finterrupted run can resume via `\u002Fresearch-pipeline — resume \u003Crun_id>` instead of restarting. Stage status splits `done` (executor finished writing) from `accepted` (the stage's cross-model gate \u002F deterministic verifier passed); resume re-validates any `done`-but-unaccepted stage. See `shared-references\u002Fresumable-runs.md`.\n\n> 💡 Override via argument, e.g., `\u002Fresearch-pipeline \"topic\" — AUTO_PROCEED: false, human checkpoint: true, difficulty: nightmare, code review: false, base repo: https:\u002F\u002Fgithub.com\u002Forg\u002Fproject, auto_write: true, venue: NeurIPS`.\n\n## Checkpoint execution rule\n\nResolve `AUTO_PROCEED` once from `$ARGUMENTS` before Stage 1 and pass that\nresolved value to nested workflows.\n\n- **`AUTO_PROCEED=true` is non-blocking.** A checkpoint is a progress update,\n  not a question. State the result and the automatically selected next action,\n  then continue executing in the **same turn**. Do not ask for confirmation,\n  request user input, sleep, wait for silence, or end the turn at a checkpoint.\n- **`AUTO_PROCEED=false` is blocking.** Present the options, ask the user, and\n  end the turn. Resume only after an explicit reply.\n\nNever implement auto-proceed as “ask, then continue if there is no response.”\nOnce a turn ends, silence cannot resume the pipeline. The user can still\ninterrupt a non-blocking run at any time.\n\nThis rule governs only `AUTO_PROCEED`-controlled selection checkpoints. If the\nuser explicitly enables a Feishu **interactive** gate, that external approval\nor reply is an intentional blocking exception; wait for that user-controlled\ngate rather than treating it as a silence timeout. Feishu off\u002Fpush-only modes\nremain non-blocking under `AUTO_PROCEED=true`.\n\n## Overview\n\nThis skill chains the entire research lifecycle into a single pipeline:\n\n```\n\u002Fidea-discovery → \u002Fexperiment-bridge → \u002Fauto-review-loop → \u002Fpaper-writing (optional)\n├── Workflow 1 ──┤├── Workflow 1.5 ──┤├── Workflow 2 ───┤ ├── Workflow 3 ──┤\n```\n\nIt orchestrates up to four major workflows in sequence. Workflow 3 (paper writing) is optional and controlled by `AUTO_WRITE`.\n\n## Resumable runs (`— resume \u003Crun_id>`)\n\nThis pipeline is long and can fail mid-run; it tracks per-stage state via\n`run_state.py` so you can resume instead of restarting (see\n[`shared-references\u002Fresumable-runs.md`](..\u002Fshared-references\u002Fresumable-runs.md)).\nSkip this whole section if `RESUMABLE = false`.\n\nResolve the helper via the canonical chain (integration-contract §2):\n`.aris\u002Ftools\u002Frun_state.py` → `tools\u002Frun_state.py` → `$ARIS_REPO\u002Ftools\u002Frun_state.py`\n→ `$ARIS_REPO\u002Ftools\u002Frun_state.py` via `~\u002F.aris\u002Frepo`\n(warn-and-skip if unresolved — never block the pipeline).\n\n**Phases**, in order: `idea-discovery, experiment-bridge, auto-review-loop, summary, paper-writing`.\n\n- **At start:** if `— resume \u003Crun_id>` was passed, run\n  `run_state.py resume \u003Croot> \u003Crun_id>` — it prints the first non-`accepted`\n  phase; **begin the pipeline at that stage** (re-run a `running`\u002F`failed` stage;\n  **re-audit** a `done`-but-unaccepted stage). Otherwise derive `\u003Crun_id>` from\n  the direction slug + date and `run_state.py start \u003Croot> \u003Crun_id> --phases\n  \"idea-discovery,experiment-bridge,auto-review-loop,summary,paper-writing\"`.\n- **Per stage:** `set \u003Crun_id> \u003Cphase> running` on entry; `set \u003Crun_id> \u003Cphase>\n  done --artifact \u003Cpath>` once the stage's artifact is written.\n- **Mark `accepted` ONLY after the stage's gate passes** — never on the executor's\n  own say-so (`run_state.py accept` requires a recorded verdict id + reviewer):\n\n  | phase | what sets `accepted` | record as reviewer |\n  |-------|----------------------|--------------------|\n  | `idea-discovery` | Gate 1 cross-model jury \u002F novelty-check passed | `codex-gpt-6-astra` + thread id |\n  | `experiment-bridge` | experiments actually ran (jobs completed) — deterministic | `deterministic:experiment-bridge` |\n  | `auto-review-loop` | the loop hit its positive STOP (`score>=6 AND verdict∈{ready,almost}` — codex's verdict) | `codex-gpt-6-astra` + final review trace id |\n  | `summary` | `NARRATIVE_REPORT.md` written (+ rendered if `RENDER_HTML`) — deterministic | `deterministic:summary` |\n  | `paper-writing` | submission audits passed (`verify_paper_audits.sh` exit 0) — deterministic | `deterministic:verify_paper_audits.sh` |\n\n**If `AUTO_WRITE = false`** (default), `paper-writing` is not part of this run:\nafter `summary` is accepted, `set \u003Crun_id> paper-writing skipped` so `resume`\nreports COMPLETE instead of pointing forever at a pending stage. Record each\n`accept` `verdict_id` as a **durable handle** — the codex thread\u002Ftrace id, or the\npath\u002Fsha of the deterministic verifier's report (e.g. the `verify_paper_audits.sh`\noutput JSON) — not just the reviewer label.\n\nA stage left `done` (gate failed\u002Fambiguous, or the run crashed before the gate)\nis re-validated on the next resume — the acceptance obligation is never skipped.\n\n## Overnight heartbeat: stall detection → forced structural pivot\n\nOnly when an unattended heartbeat is driving this run (overnight `\u002Floop` \u002F\n`CronCreate`). Skip otherwise. Doctrine + rationale:\n[`shared-references\u002Fexternal-cadence.md`](..\u002Fshared-references\u002Fexternal-cadence.md)\n→ \"Stall detection & forced structural pivot\". This is a Type-A signal — it counts\nfindings and changes *direction*, never *judges quality*.\n\nResolve the helper via the canonical chain (integration-contract §2), warn-and-skip\nif unresolved (never block the run):\n```bash\nITER_LOG=\".aris\u002Ftools\u002Fiteration_log.py\"\n[ -f \"$ITER_LOG\" ] || ITER_LOG=\"tools\u002Fiteration_log.py\"\n[ -f \"$ITER_LOG\" ] || ITER_LOG=\"${ARIS_REPO:-}\u002Ftools\u002Fiteration_log.py\"\n[ -f \"$ITER_LOG\" ] || { [ -z \"${ARIS_REPO:-}\" ] && [ -f \"$HOME\u002F.aris\u002Frepo\" ] && ARIS_REPO=\"$(cat \"$HOME\u002F.aris\u002Frepo\" 2>\u002Fdev\u002Fnull)\"; } || true\n[ -f \"$ITER_LOG\" ] || ITER_LOG=\"${ARIS_REPO:-}\u002Ftools\u002Fiteration_log.py\"\n[ -f \"$ITER_LOG\" ] || { echo \"WARN: iteration_log.py not resolved; skipping stall detection\" >&2; ITER_LOG=\"\"; }\n```\nThen, **each heartbeat tick**, record how many concrete new findings the current\nstage produced and read the returned `pivot`:\n```bash\n[ -n \"$ITER_LOG\" ] && python3 \"$ITER_LOG\" note \"$ROOT\" \"$RUN_ID\" \"$STAGE\" \"$N_NEW_FINDINGS\"\n# → {\"stale_count\": N, \"pivot\": \"none|structural|human\"}\n```\nAct on `pivot`:\n- `none` — keep going.\n- `structural` (stale ≥ 2) — the next nudge must change a **structural constraint**\n  (frame \u002F objective \u002F data \u002F representation), not a tactical parameter, and pick a\n  direction different from every one already tried. Record the chosen frame so future\n  ticks can avoid it: `python3 \"$ITER_LOG\" note \"$ROOT\" \"$RUN_ID\" \"$STAGE\" 0 --direction \"\u003Cthe new frame>\"`.\n- `human` (stale ≥ 4) — stop nudging blindly; flag for human attention (escalate, do\n  not silently abandon).\n\nThe heartbeat may say \"keep going \u002F change direction,\" never \"good enough\" — every\nquality verdict still terminates in the cross-model jury (`acceptance-gate.md`).\n\n## Pipeline\n\n### Stage 1: Idea Discovery (Workflow 1)\n\nIf `RESEARCH_BRIEF.md` exists in the project root, it will be automatically loaded as detailed context (replaces one-line prompt). See `templates\u002FRESEARCH_BRIEF_TEMPLATE.md`.\n\nInvoke the idea discovery pipeline:\n\n```\n\u002Fidea-discovery \"$ARGUMENTS\" — AUTO_PROCEED: $AUTO_PROCEED\n```\n\nThis internally runs: `\u002Fresearch-lit` → `\u002Fidea-creator` → `\u002Fnovelty-check` → `\u002Fresearch-review`\n\n**Output:** `idea-stage\u002FIDEA_REPORT.md` with ranked, validated, pilot-tested ideas.\n\n**🚦 Gate 1 — Idea Selection:**\n\nAfter `idea-stage\u002FIDEA_REPORT.md` is generated, present the top ideas.\n\n**If `AUTO_PROCEED=true` (non-blocking):** report the selection and continue\nimmediately in the same turn. Do not phrase the update as a question:\n\n```\n📋 Idea Discovery complete. Top ideas:\n\n1. [Idea 1 title] — Pilot: POSITIVE (+X%), Novelty: CONFIRMED\n2. [Idea 2 title] — Pilot: WEAK POSITIVE (+Y%), Novelty: CONFIRMED\n3. [Idea 3 title] — Pilot: NEGATIVE, eliminated\n\nAUTO_PROCEED: selected Idea 1 — [title]. Continuing to Stage 2.\n```\n\n**If `AUTO_PROCEED=false` (blocking):** present the same ranking, ask\n`Recommended: Idea 1. Shall I proceed with implementation?`, then end the turn.\nThe user may:\n- **Approve the idea** → proceed to Stage 2. `\u002Fexperiment-bridge` reads `refine-logs\u002FEXPERIMENT_PLAN.md` already generated by `\u002Fidea-discovery`.\n- **Request changes** (e.g., \"combine Idea 1 and 3\", \"focus more on X\") → update the idea prompt with user feedback, re-run `\u002Fidea-discovery` with refined constraints, and present again.\n- **Reject all ideas** → collect feedback on what's missing, re-run Stage 1 with adjusted research direction. Repeat until the user commits to an idea.\n- **Stop here** → save current state to `idea-stage\u002FIDEA_REPORT.md` for future reference.\n\n> ⚠️ **This gate waits for user confirmation when AUTO_PROCEED=false.** When `true`, it auto-proceeds after presenting results. The rest of the pipeline (Stages 2-3) is expensive (GPU time + multiple review rounds), so set `AUTO_PROCEED=false` if you want a final review checkpoint before committing GPU resources.\n\n### Stage 2: Experiment Bridge (Workflow 1.5)\n\nOnce the idea is selected (automatically or by the user), delegate implementation and deployment to `\u002Fexperiment-bridge`:\n\n```\n\u002Fexperiment-bridge \"$CHOSEN_IDEA_TITLE\" — code review: $CODE_REVIEW, base repo: $BASE_REPO, compact: $COMPACT\n```\n\n> 💡 **Queue routing is automatic**: `\u002Fexperiment-bridge` Phase 4 routes each milestone by job count — ≤5 jobs → `\u002Frun-experiment`, ≥10 jobs or teacher→student phase dependencies → `\u002Fexperiment-queue` (with OOM retry, wave gating, crash-safe state). No manual override is needed.\n\n**What this does (fully autonomous):**\n1. Parses `refine-logs\u002FEXPERIMENT_PLAN.md` — extracts milestones, run order, compute budget\n2. Implements experiment code — extends pilot to full scale, follows existing codebase conventions\n3. **Cross-model code review** — GPT-6-Astra xhigh reviews the implementation for logic bugs, incorrect metrics, and ground-truth misuse before any GPU time is spent\n4. **Sanity check** — runs the smallest experiment first to verify the environment; auto-debugs failures (up to 3 attempts, with `\u002Fcodex:rescue` fallback)\n5. Deploys full experiments — auto-routes by job count (≤5 → `\u002Frun-experiment`, ≥10 → `\u002Fexperiment-queue` with OOM retry, wave gating, crash-safe state)\n6. Collects initial results — parses outputs, updates `refine-logs\u002FEXPERIMENT_TRACKER.md`, runs `\u002Ftraining-check` if W&B is configured\n7. Auto-plans ablations via `\u002Fablation-planner` if main results are positive\n\n**Output:**\n- `refine-logs\u002FEXPERIMENT_RESULTS.md` — structured results by milestone\n- `refine-logs\u002FEXPERIMENT_TRACKER.md` — updated run-by-run status\n- `EXPERIMENT_LOG.md` (when `COMPACT=true`) — session-recovery-friendly log\n\n**Monitor progress** (while experiments run):\n\n```\n\u002Fmonitor-experiment [server]\n```\n\nWait for `\u002Fexperiment-bridge` to complete and report its handoff summary before proceeding.\n\n### Stage 3: Auto Review Loop (Workflow 2)\n\nOnce initial results are in, start the autonomous improvement loop:\n\n```\n\u002Fauto-review-loop \"$ARGUMENTS — [chosen idea title], difficulty: $REVIEWER_DIFFICULTY\"\n```\n\n**What this does (up to 4 rounds):**\n1. GPT-6-Astra xhigh reviews the work (score, weaknesses, minimum fixes)\n2. Claude Code implements fixes (code changes, new experiments, reframing)\n3. Deploy fixes, collect new results\n4. Re-review → repeat until (score ≥ 6\u002F10 AND verdict ∈ {ready, almost}) or 4 rounds reached\n\n**Output:** `review-stage\u002FAUTO_REVIEW.md` with full review history and final assessment.\n\n### Stage 4: Research Summary & Writing Handoff\n\nAfter the auto-review loop completes, prepare the handoff for paper writing.\n\n**Step 1:** Write a final research status report (same as before).\n\n**Step 2:** Generate `NARRATIVE_REPORT.md` from:\n- `IDEA_REPORT.md` (chosen idea, hypothesis, novelty justification)\n- Implementation details from the repo\n- Experiment configs and final results\n- `AUTO_REVIEW.md` (review history, weaknesses fixed, remaining limitations)\n\nThe narrative report must contain:\n- Problem statement and core claim\n- Method summary\n- Key quantitative results with evidence for each claim\n- Figure\u002Ftable inventory (which exist, which need manual creation)\n- Limitations and remaining follow-up items\n\n**Output:** `NARRATIVE_REPORT.md` + research pipeline report.\n\n```markdown\n# Research Pipeline Report\n\n**Direction**: $ARGUMENTS\n**Chosen Idea**: [title]\n**Date**: [start] → [end]\n**Pipeline**: idea-discovery → experiment-bridge → auto-review-loop\n\n## Journey Summary\n- Ideas generated: X → filtered to Y → piloted Z → chose 1\n- Implementation: [brief description of what was built]\n- Experiments: [number of GPU experiments, total compute time]\n- Review rounds: N\u002F4, final score: X\u002F10\n\n## Writing Handoff\n- NARRATIVE_REPORT.md: ✅ generated\n- Venue: [VENUE or \"not set — run \u002Fpaper-writing manually\"]\n- Manual figures needed: [list or \"none\"]\n\n## Remaining TODOs (if any)\n- [items flagged by reviewer that weren't addressed]\n```\n\n### Stage 5: Paper Writing (Workflow 3 — Optional)\n\n**Skip this stage if `AUTO_WRITE=false` (default).** Present the `\u002Fpaper-writing` command for manual use:\n\n```\n📝 Research complete. To write the paper:\n\u002Fpaper-writing \"NARRATIVE_REPORT.md\" — venue: \u003CVENUE>, AUTO_PROCEED: $AUTO_PROCEED\n```\n\n**If `AUTO_WRITE=true`:**\n\n🚦 **Gate 2 — Writing Checkpoint:**\n\n```\n📝 Research pipeline complete. Ready for Workflow 3.\n\n- Venue: [VENUE]\n- Input: NARRATIVE_REPORT.md\n- Manual figures required: [list or none]\n- Next step: \u002Fpaper-writing \"NARRATIVE_REPORT.md\" — venue: [VENUE], AUTO_PROCEED: $AUTO_PROCEED\n\nProceeding with paper writing...\n```\n\nChecks before proceeding (venue binds HERE — Stages 1-4 are venue-independent):\n- If `VENUE` is missing: with `AUTO_PROCEED=false`, ask now. With\n  `AUTO_PROCEED=true`, do not guess and do not wait — stamp\n  \"VENUE NOT SPECIFIED — paper writing deferred\" in the report and checkpoint,\n  leave the paper-writing phase pending, and finish the run cleanly for a later\n  resume. Never silently pick a venue.\n- If manual figures are required: with `AUTO_PROCEED=false`, pause and list\n  them. With `AUTO_PROCEED=true`, record \"paper writing deferred (manual\n  figures: \u003Clist>)\" and finish cleanly the same way.\n\nThen invoke:\n\n```\n\u002Fpaper-writing \"NARRATIVE_REPORT.md\" — venue: $VENUE, AUTO_PROCEED: $AUTO_PROCEED\n```\n\nPass the resolved `AUTO_PROCEED` explicitly so Workflow 3 cannot silently\nfall back to its own default mode.\n\nThis delegates to Workflow 3 which handles its own phases:\n`\u002Fpaper-plan → \u002Fpaper-figure → \u002Fpaper-write → \u002Fpaper-compile → \u002Fauto-paper-improvement-loop`\n\nWhen Workflow 3 finishes, update the pipeline report with:\n- Paper writing completion status\n- Final PDF path (`paper\u002Fmain.pdf`)\n- Improvement scores (round 0 → round N)\n- Remaining issues\n\n**Output:** `paper\u002F` directory with LaTeX source, compiled PDF, and `PAPER_IMPROVEMENT_LOG.md`.\n\n## Render HTML view (auto, when `RENDER_HTML = true`)\n\nAfter Stage 4 finalizes `NARRATIVE_REPORT.md` (before paper writing branches), invoke `\u002Frender-html` on the narrative report:\n\n```\n\u002Frender-html \"NARRATIVE_REPORT.md\" --no-review\n```\n\n`--no-review` is intentional: this is an internal handoff doc, not reviewer-facing — the claims it summarizes were already cross-model-reviewed in Stage 3's `\u002Fauto-review-loop`. Output: `NARRATIVE_REPORT.html` next to the MD, with embedded source SHA256.\n\n**Non-blocking**: if `\u002Frender-html` fails (helper missing, file write error, etc.), log the failure and continue Stage 4 — the HTML view is a convenience artifact, not a pipeline prerequisite.\n\nSkip this step if `RENDER_HTML = false`.\n\n## Output Protocols\n\n> Follow these shared protocols for all output files:\n> - **[Output Versioning Protocol](..\u002Fshared-references\u002Foutput-versioning.md)** — write timestamped file first, then copy to fixed name\n> - **[Output Manifest Protocol](..\u002Fshared-references\u002Foutput-manifest.md)** — log every output to MANIFEST.md\n> - **[Output Language Protocol](..\u002Fshared-references\u002Foutput-language.md)** — respect the project's language setting\n\n## Key Rules\n\n- **Large file handling**: If the Write tool fails due to file size, immediately retry using Bash (`cat \u003C\u003C 'EOF' > file`) to write in chunks. Do NOT ask the user for permission — just do it silently.\n\n- **The Stage 1 checkpoint is controlled by AUTO_PROCEED.** When `false`, do not proceed without user confirmation. When `true`, report the top selection and continue in the same turn without asking or waiting.\n- **Stages 2-3 can run autonomously** once the idea is selected. This is the \"sleep and wake up to results\" part.\n- **If Stage 3 ends at round 4 without positive assessment**, stop and report remaining issues. Do not loop forever.\n- **Budget awareness**: Track total GPU-hours across the pipeline. Flag if approaching user-defined limits.\n- **Documentation**: Every stage updates its own output file. The full history should be self-contained.\n- **Fail gracefully**: If any stage fails (no good ideas, experiments crash, review loop stuck), report clearly and suggest alternatives rather than forcing forward.\n\n## Typical Timeline\n\n| Stage | Duration | Can sleep? |\n|-------|----------|------------|\n| 1. Idea Discovery | 30-60 min | Yes if AUTO_PROCEED=true |\n| 2. Experiment Bridge | 30-120 min (implement + review + deploy + collect) | Yes ✅ |\n| 3. Auto Review | 1-4 hours (depends on experiments) | Yes ✅ |\n\n**Sweet spot**: Run Stage 1 in the evening, launch Stage 2-3 before bed, wake up to a reviewed paper.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex, mcp__codex__codex-reply","[research-direction] [— resume \u003Crun_id>]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fresearch-pipeline",0,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science","https:\u002F\u002Fgithub.com\u002FCZX-LBJ","一个没事喜欢随便写点代码的小菜鸡\r\n","2026-10-22 09:48:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill research-pipeline",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill research-pipeline",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill research-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fresearch-pipeline\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7FEEKSNMRMKW6JEK93PFDFY","bio-free-energy-calculations","Performs alchemical free-energy calculations including relative binding free energy (RBFE \u002F FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda scheduling, soft-core potentials, MBAR\u002FBAR analysis, cycle-closure validation, and protocol-appropriate enhanced sampling. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Ffree-energy-calculations\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7FEE5CTE5QK55CEMXNNVWY9","bio-conformer-generation","Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94\u002FUFF force-field optimization, CREST + GFN2-xTB semi-empirical refinement, and macrocycle-aware torsion preferences. Provides explicit decision rules for single vs ensemble conformer use, RMSD pruning, energy windows, conformer count, and force-field choice. Use when preparing 3D ligands for docking, generating descriptor input for 3D QSAR, or sampling macrocycle\u002Fpeptide conformational ensembles.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fconformer-generation\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FEDNGFEMFWD1MSEDR5H7CY","bio-admet-prediction","Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG\u002FCYP\u002FAMES endpoints, and PAINS \u002F Lipinski \u002F Ro5 \u002F Veber \u002F BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fadmet-prediction\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers","Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FECVVDWZ0X0VEDTCE4B4DZ","wiki-enrich","Fill in the per-paper TODO sections of research-wiki\u002Fpapers\u002F\u003Cslug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers\u002F as TODO scaffolds.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwiki-enrich\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FECD4BCJ2MTSBDDSE3ZAJ5","web-debug-search","Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fweb-debug-search\u002FSKILL.md",[],[]]