Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.

Workflow 1: Idea Discovery Pipeline Orchestrate a complete idea discovery workflow for: $ARGUMENTS Overview This skill chains sub skills into a single automated pipeline: Each phase builds on the previous one's output. The final deliverables are a validated idea stage/IDEA REPORT.md with ranked ideas, plus a refined proposal ( refine logs/FINAL PROPOSAL.md ) and experiment plan ( refine logs/EXPERIMENT PLAN.md ) for the top idea. Constants PILOT MAX HOURS = 2 — Skip any pilot experiment estimated to take 2 hours per GPU. Flag as "needs manual pilot" in the report. PILOT TIMEOUT HOURS = 3 — Hard timeout: kill any running pilot that exceeds 3 hours. Collect partial results if available. MAX PILOT IDEAS = 3 — Run pilots for at most 3 top ideas in parallel. Additional ideas are validated on paper only. MAX TOTAL GPU HOURS = 8 — Total GPU budget across all pilots. If exceeded, skip remaining pilots and note in report. AUTO PROCEED = true — When true , checkpoints are informational: report the selected option and continue in the same turn. Set to false to ask for explicit user confirmation and end the turn at each selection checkpoint. REVIEWER MODEL = gpt 6 astra — Model used via Codex MCP. Must be an OpenAI model (e.g., gpt 6 astra , o3 , gpt 4o ). Passed to sub skills. OUTPUT DIR = idea stage/ — All idea stage outputs go here. Create the directory if it doesn't exist. ARXIV DOWNLOAD = false — When true , /research lit downloads the top relevant arXiv PDFs during Phase 1. When false (default), only fetches metadata. Passed through to /research lit . COMPACT = false — When true , generate compact summary files for short context models and session recovery. Writes idea stage/IDEA CANDIDATES.md (top 3 5 ideas only) at the end of this workflow. Downstream skills read this instead of the full idea stage/IDEA REPORT.md . RENDER HTML = true — When true (default), auto render idea stage/IDEA REPORT.md to HTML at workflow end via /render html . Uses no review (the source MD already went through novelty + cross model review during Phase 3). Set false to skip, or pass — render html: false . REF PAPER = false — Reference paper to base ideas on. Accepts: local PDF path, arXiv URL, or any paper URL. When set, the paper is summarized first ( idea stage/REF PAPER SUMMARY.md ), then idea generation uses it as context. Combine with base repo for "improve this paper with this codebase" workflows. RESUMABLE = true — Record stage evidence under .aris/runs/<run id .json and require a deterministic evidence gate before declaring the final report complete. 💡 These are defaults. Override by telling the skill, e.g., /idea discovery "topic" — ref paper: https://arxiv.org/abs/2406.04329 or /idea discovery "topic" — compact: true . Checkpoint execution rule Resolve AUTO PROCEED once from $ARGUMENTS before Phase 0 and keep that mode for the entire workflow. AUTO PROCEED=true is non blocking. A checkpoint is a progress update, not a question. State the result and the automatically selected next action, then continue executing in the same turn . Do not ask for confirmation, request user input, sleep, wait for silence, or end the turn at a checkpoint. AUTO PROCEED=false is blocking. Present the options, ask the user, and end the turn. Resume only after an explicit reply. Never implement auto proceed as “ask, then continue if there is no response.” Once a turn ends, silence cannot resume the workflow. The user can still interrupt a non blocking run at any time. This rule governs only AUTO PROCEED controlled selection checkpoints. If the user explicitly enables a Feishu interactive gate, that external approval or reply is an intentional blocking exception; wait for that user controlled gate rather than treating it as a silence timeout. Feishu off/push only modes remain non blocking under AUTO PROCEED=true . Per stage evidence gate ( RESUMABLE = true ) Resolve run state.py and idea discovery gate.py through the same canonical helper chain used by /research pipeline : .aris/tools/ → tools/ → $ARIS REPO/tools/ → ~/.aris/repo/tools/ . If either helper is unavailable, the final report is BLOCKED ; do not silently continue without a state record. For a new run, derive <run id from the direction slug and date, then start this ordered state record with executor <actual Claude model (for example, claude sonnet 4.5 ): For each phase, mark running on entry and done artifact <path only after its artifact is present. Use these artifact locators so the final gate can check the canonical report rather than scattered scratch files: Phase Artifact locator research lit idea stage/IDEA REPORT.md literature landscape idea creator idea stage/IDEA REPORT.md ranked ideas novelty check idea stage/IDEA REPORT.md novelty verification research review idea stage/IDEA REPORT.md external critical review research refine pipeline refine logs/FINAL PROPOSAL.md novelty check and research review are reviewer bearing phases . A done status or a heading alone is not review evidence. After each phase has folded substantive findings into its anchored report section, first record it done , then, only after the configured reviewer actually returns a positive, identity bearing verdict, record the cross family receipt using the actual returned model and durable thread/trace id: Never invent either value and never call accept without the positive verdict required by the run state contract. For novelty check , both PROCEED and PROCEED WITH CAUTION are positive verdicts — caution is guidance for the pilot, not a rejection; only ABANDON is negative. For research review , positive means the review's bottom line does not argue for abandoning the idea — a list of named risks is not a rejection. If the review ends without a clear stance, ask the same reviewer thread for a one line verdict (proceed or abandon) and record on that answer; never infer positivity from silence. A negative verdict does not grant a review receipt. Leave the phase done and the final gate BLOCKED , select a surviving or new idea, then re run that reviewer bearing phase. Do the same if the reviewer is unavailable, returns no valid identity/response, or its output was not folded into the report. At the end of Phase 5, run: The gate writes its result to gates.idea discovery evidence in the run state. On PASS , it has validated (but never created) the two review receipts, all required artifacts, and non empty anchored report sections. Per phase acceptance stays with each stage's own cross model gate. On a non zero exit, it writes explicit BLOCKED: <stage evidence missing lines to the report; do not present the workflow as complete. On — resume <run id , start from the first non terminal phase and re run the gate before finalizing. Pipeline Phase 0: Load Research Brief (if available) Before starting any other phase, check for a detailed research brief in the project: 1. Look for RESEARCH BRIEF.md in the project root (or path passed as $ARGUMENTS ) 2. If found, read it and extract: Problem statement and context Constraints (compute, data, timeline, venue) What the user already tried / what didn't work Domain knowledge and non goals Existing results (if any) 3. Use this as the primary context for all subsequent phases — it replaces the one line prompt 4. If both RESEARCH BRIEF.md and a one line $ARGUMENTS exist, merge them (brief takes priority for details, argument sets the direction) If no brief exists, proceed normally with $ARGUMENTS as the research direction. 💡 Create a brief from the template: cp templates/RESEARCH BRIEF TEMPLATE.md RESEARCH BRIEF.md — keep it to ~1 2 pages (4 8k chars); long material goes in separate files referenced by path. Phase 0.5: Reference Paper Summary (when REF PAPER is set) Skip entirely if REF PAPER is false . Summarize the reference paper before searching the literature: 1. If arXiv URL (e.g., https://arxiv.org/abs/2406.04329 ): Invoke /arxiv "ARXIV ID" — download to fetch the PDF Read the first 5 pages (title, abstract, intro, method overview) 2. If local PDF path (e.g., papers/reference.pdf ): Read the PDF directly (first 5 pages) 3. If other URL : Fetch and extract content via WebFetch 4. Generate idea stage/REF PAPER SUMMARY.md : 🚦 Checkpoint: Present the summary to the user: Phase 1 and Phase 2 will use idea stage/REF PAPER SUMMARY.md as additional context — /research lit searches for related and competing work, /idea creator generates ideas that build on or improve the reference paper. Phase 1: Literature Survey Invoke /research lit to map the research landscape. Idea discovery is exactly the place where Gemini's AI driven broad coverage adds value, so include gemini as a source by default unless the user already specified an explicit — sources: directive in their idea discovery invocation: — composed: idea stage/IDEA REPORT.md puts /research lit in composed mode (see Output hygiene above): it returns the landscape for folding into the report instead of writing a standalone landscape file. The report doesn't exist yet at Phase 1 — the directive names the forthcoming canonical doc, and /idea creator creates it in Phase 2. If gemini cli is not installed, /research lit skips the Gemini source gracefully with a warning — no break to the pipeline. Users who want to force disable Gemini in idea discovery can pass /idea discovery "topic" — sources: all explicitly (which becomes the literal source list, no auto injection). What this does: Search arXiv, Google Scholar, Semantic Scholar for recent papers Plus Gemini driven broad discovery (sub problem decomposition, naming variants, alias coverage) when gemini cli is available Build a landscape map: sub directions, approaches, open problems Identify structural gaps and recurring limitations Output a literature summary (saved to working notes) 🚦 Checkpoint: Present the landscape summary to the user. When AUTO PROCEED=true (non blocking): report the selected direction and continue immediately in the same turn, without a question: When AUTO PROCEED=false (blocking): present the same findings, ask Does this match your understanding? Should I adjust the scope before generating ideas? , then end the turn. User approves → proceed to Phase 2 with the best direction. User requests changes (e.g., "focus more on X", "ignore Y", "too broad") → refine the search with updated queries, re run /research lit with adjusted scope, and present again. Repeat until the user is satisfied. Phase 2: Idea Generation + Filtering + Pilots Invoke /idea creator with the landscape context (and idea stage/REF PAPER SUMMARY.md if available): /idea creator owns idea stage/IDEA REPORT.md as the canonical deliverable; the — composed: directive tells it to fold the survey/novelty findings in rather than emitting LIT LANDSCAPE.md / RESEARCH REVIEW.md / MANIFEST.md alongside. What this does: If idea stage/REF PAPER SUMMARY.md exists, include it as context — ideas should build on, improve, or extend the reference paper Brainstorm 8 12 concrete ideas via GPT 6 Astra xhigh Filter by feasibility, compute cost, quick novelty search Deep validate top ideas (full novelty check + devil's advocate) Run parallel pilot experiments on available GPUs (top 2 3 ideas) Rank by empirical signal Output idea stage/IDEA REPORT.md 🚦 Checkpoint: Present idea stage/IDEA REPORT.md ranked ideas to the user. When AUTO PROCEED=true (non blocking): report the automatic selection and continue immediately in the same turn, without a question: When AUTO PROCEED=false (blo

idea-discovery