idea-creator
Skill9 starsChanged 3 months agoMITView on GitHub
Prompt-only by default in the lightweight pack; Claude/Gemini reviewer transport is explicit opt-in. Generate and rank research ideas given a broad direction. Use when user says \"\u627eidea\", \"brainstorm ideas\", \"generate research ideas\", \"what can we work on\", or wants to explore a research area for publishable directions.
7 other projects use a version of this, 7 of them edited.
Adopted by
Most recently taken up by
- yvesory/academic-research-suiteedited, first seen Oct 9, 2026
- talhaMah56/claude_skillsedited, first seen Sep 12, 2026
- wanshuiyin/Auto-claude-code-research-in-sleepedited, first seen Jul 15, 2026
- zjunlp/Mechanistedited, first seen Jul 11, 2026
- Chanw-research/claude-code-paper-writingedited, first seen May 10, 2026
- raja21068/AutoResearchedited, first seen May 5, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 7
- wanshuiyin/Auto-claude-code-research-in-sleep★ 19k17% same
- zjunlp/Mechanist★ 7562% same
- Chanw-research/claude-code-paper-writing★ 4261% same
- yvesory/academic-research-suite★ 953% same
- Yusong-Enceladus/claude-skills★ 882% same
- raja21068/AutoResearch★ 261% same
- talhaMah56/claude_skills★ 030% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- autodl-hpcSkill
- experiment-bridgeSkill
- experiment-planSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
- autodl-hpcSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-writeSkill
- research-refineSkill
- research-reviewSkill
- experiment-bridgeSkill
- experiment-planSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- grant-proposalSkill
- idea-discoverySkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-posterSkill
- paper-slidesSkill
- paper-writeSkill
- paper-writingSkill
- research-refineSkill
- research-reviewSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
27 rules. 7 are common, 3 are distinctive, and 17 are very specific to this project.
7
Common
Most of the 7 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
17
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Write the review prompt under review-prompts/ and ask the user to run it in a separate conversation with the relevant skills enabled.
- Distinctive: line 16
Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.
- Very specific: line 18
Use pasted review text as the external verdict, then write compact summaries such as REVIEW_SUMMARY.md, NEXT_ACTIONS.md, or the …
- Distinctive: line 20
Keep heavy experiments AutoDL/HPC-gated and user-approved.
- Very specific: line 47
Before the landscape survey, check idea-stage/TOPIC_CANDIDATES.md.
- Distinctive: line 62
When reference-led seeds exist, use their source locators as starting queries, then test each asserted gap against broader and more recent …
- Very specific: line 67
Scan local paper library first: Check papers/ and literature/ in the project directory for existing PDFs.
- Common: line 72
Use 5+ different query formulations
- Common: line 73
Read abstracts and introductions of the top 10-15 papers
- Very specific: line 90
Use the local gemini-review MCP bridge for divergent thinking:
- Very specific: line 132
After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until …
- Very specific: line 149
Novelty signal — ANNOTATE, do not eliminate: do 2-3 targeted searches and attach a prior_work note (what looks related, with links).
- Very specific: line 159
Every feasible, non-duplicate idea — with its prior_work and so_what annotations — proceeds to Phase 4, where the cross-model reviewer does …
- Very specific: line 167
Novelty check: Use the /novelty-check workflow (multi-source search + Gemini cross-verification) for each idea
- Very specific: line 169
Critical review: Use mcp__gemini-review__review_reply_start with the saved completed threadId:
- Very specific: line 184
After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until …
- Common: line 190
Before committing to a full research effort, run cheap pilot experiments to get empirical signal.
- Very specific: line 195
Estimate GPU-hours BEFORE launching: If estimated time > PILOT_MAX_HOURS, reduce scale (fewer epochs, smaller subset) or flag as "needs …
- Very specific: line 198
Deploy in parallel: Use /run-experiment to launch pilots on different GPUs simultaneously:
- Very specific: line 204
Use run_in_background: true to launch all at once.
- Very specific: line 206
Collect results: Use /monitor-experiment to check progress.
- Common: line 212
Re-rank based on empirical evidence: Update the idea ranking using pilot results.
- Very specific: line 218
Write a structured report to idea-stage/IDEA_REPORT.md:
- Very specific: line 284
Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks.
- Common: line 289
Don't fall in love with any idea before validating it.
- Common: line 290
Always estimate compute cost.
- Common: line 297
After this skill produces the ranked report:
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Override for Codex users who want Gemini, not a second Codex agent, to act as the reviewer. Install this package after
skills/skills-codex/*.
Customized Pack Defaults
This reviewer overlay is opt-in transport only. In the customized lightweight pack, default to prompt-only review unless the user explicitly asks to use this overlay reviewer backend:
- Write the review prompt under
review-prompts/and ask the user to run it in a separate conversation with the relevant skills enabled. - Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.
- Use pasted review text as the external verdict, then write compact summaries
such as
REVIEW_SUMMARY.md,NEXT_ACTIONS.md, or the skill-specific log. - Keep heavy experiments AutoDL/HPC-gated and user-approved; local work stays at edits, tests, lint, dry-runs, and tiny smoke checks.
Research Idea Creator
Generate publishable research ideas for: $ARGUMENTS
Overview
Given a broad research direction from the user, systematically generate, validate, and rank concrete research ideas. This skill composes with /research-lit, /novelty-check, and /research-review to form a complete idea discovery pipeline.
Constants
- PILOT_MAX_HOURS = 2 — Skip any pilot estimated to take > 2 hours per GPU. Flag as "needs manual pilot".
- PILOT_TIMEOUT_HOURS = 3 — Hard timeout: kill pilots exceeding 3 hours. Collect partial results if available.
- MAX_PILOT_IDEAS = 3 — Pilot at most 3 ideas in parallel. Additional ideas are validated on paper only.
- MAX_TOTAL_GPU_HOURS = 8 — Total GPU budget for all pilots combined.
- REVIEWER_MODEL =
gemini-review— Gemini reviewer invoked through the localgemini-reviewMCP bridge for brainstorming and critique. SetGEMINI_REVIEW_MODELif you need a specific Gemini model override. - OUTPUT_DIR =
idea-stage/— Directory for idea output files.
💡 Override via argument, e.g.,
/idea-creator "topic" — pilot budget: 4h per idea, 20h total.
Workflow
Phase 0: Load Reference-Led Topic Seeds (if available)
Before the landscape survey, check idea-stage/TOPIC_CANDIDATES.md. If it
exists, read it as a compact evidence handoff. Consult
idea-stage/REFERENCE_DECONSTRUCTION.md only when a locator or boundary needs
interpretation; do not redo its paper or figure evidence extraction.
For every carried seed, preserve its candidate ID, gap source type, source
locators, gate status, minimum discriminating evidence, and conclusion boundary.
A ready_for_novelty_check seed is still unverified; needs_evidence becomes
an explicit research task; blocked remains excluded unless a narrower
repairable question is supported.
Phase 1: Landscape Survey (5-10 min)
Map the research area to understand what exists and where the gaps are.
When reference-led seeds exist, use their source locators as starting queries, then test each asserted gap against broader and more recent literature. Keep the seed's status and conclusion boundary visible in the landscape; do not turn a single paper's future-work statement or limitation into a field-wide claim.
- Scan local paper library first: Check
papers/andliterature/in the project directory for existing PDFs. Read first 3 pages of relevant papers to build a baseline understanding before searching online. This avoids re-discovering what the user already knows. - Search recent literature using WebSearch:
- Top venues in the last 2 years (NeurIPS, ICML, ICLR, ACL, EMNLP, etc.)
- Recent arXiv preprints (last 6 months)
- Use 5+ different query formulations
- Read abstracts and introductions of the top 10-15 papers
- Build a landscape map:
- Group papers by sub-direction / approach
- Identify what has been tried and what hasn't
- Note recurring limitations mentioned in "Future Work" sections
- Flag any open problems explicitly stated by multiple papers
- Identify structural gaps:
- Methods that work in domain A but haven't been tried in domain B
- Contradictory findings between papers (opportunity for resolution)
- Assumptions that everyone makes but nobody has tested
- Scaling regimes that haven't been explored
- Diagnostic questions that nobody has asked
Phase 2: Idea Generation (brainstorm with external LLM)
Use the local gemini-review MCP bridge for divergent thinking:
mcp__gemini-review__review_start:
prompt: |
You are a senior ML researcher brainstorming research ideas.
Research direction: [user's direction]
Here is the current landscape:
[paste landscape map from Phase 1]
Key gaps identified:
[paste gaps from Phase 1]
Reference-led topic seeds (optional):
[paste candidate ID, source locators, gate status, minimum discriminating
evidence, and conclusion boundary from TOPIC_CANDIDATES.md]
Treat a seed as a constrained starting point, not a novelty verdict. For
every idea descended from a seed, preserve its provenance and do not claim
more than its recorded conclusion boundary. `needs_evidence` means the
missing evidence must appear in the validation plan; `blocked` is not a
candidate to promote without a narrower, evidence-backed repair.
Generate 8-12 concrete research ideas. For each idea:
1. One-sentence summary
2. Core hypothesis (what you expect to find and why)
3. Minimum viable experiment (what's the cheapest way to test this?)
4. Expected contribution type: empirical finding / new method / theoretical result / diagnostic
5. Risk level: LOW (likely works) / MEDIUM (50-50) / HIGH (speculative)
6. Estimated effort: days / weeks / months
Prioritize ideas that are:
- Testable with moderate compute (8x RTX 3090 or less)
- Likely to produce a clear positive OR negative result (both are publishable)
- Not "apply X to Y" unless the application reveals genuinely surprising insights
- Differentiated from the 10-15 papers above
Be creative but grounded. A great idea is one where the answer matters regardless of which way it goes.After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until done=true. Treat the completed status payload's response as the brainstorm output, and save the completed threadId for follow-up critique in Phase 4.
Phase 3: Mechanical consolidation + objective feasibility gate
This phase does NOT judge idea quality, novelty, or impact — those are the job of the Phase-4 cross-model reviewer (a different model family). Dropping ideas here on a same-family novelty or impact call would pre-filter the reviewer's input with same-family judgment — the opposite of why debuffer uses a cross-model reviewer at all. Phase 3 only (a) clusters near-duplicate ideas and (b) drops ideas that are OBJECTIVELY out of budget; everything else passes through ANNOTATED, not eliminated.
- Objective feasibility gate (safe to gate here): drop an idea ONLY on a mechanical, budget-based fact — estimated compute > 1 week of available GPU time, OR a dataset that is provably unavailable. Do NOT drop on "implementation looks complex" — annotate complexity instead.
- Novelty signal — ANNOTATE, do not eliminate: do 2-3 targeted searches
and attach a
prior_worknote (what looks related, with links). This is input for the Phase-4 reviewer, not a filter; full/novelty-checkruns in Phase 4. Do NOT drop an idea here because it "might already be done." - Impact signal — ANNOTATE, do not eliminate: attach a one-line
so_whatnote (why the result would matter either way). Do NOT drop on a same-family "a reviewer wouldn't care" call — that is exactly what the Phase-4 cross-model reviewer is for.
Every feasible, non-duplicate idea — with its prior_work and so_what
annotations — proceeds to Phase 4, where the cross-model reviewer does the
quality/novelty narrowing.
Phase 4: Deep Validation (for top ideas)
For each surviving idea, run a deeper evaluation:
- Novelty check: Use the
/novelty-checkworkflow (multi-source search + Gemini cross-verification) for each idea Critical review: Use
mcp__gemini-review__review_reply_startwith the saved completedthreadId:mcp__gemini-review__review_reply_start: threadId: [saved completed threadId from Phase 2] prompt: | Here are our top ideas after filtering: [paste surviving ideas with novelty check results] For each, play devil's advocate: - What's the strongest objection a reviewer would raise? - What's the most likely failure mode? - How would you rank these for a top venue submission? - Which 2-3 would you actually work on?After this start call, immediately save the returned
jobIdand pollmcp__gemini-review__review_statuswith a boundedwaitSecondsuntildone=true. Treat the completed status payload'sresponseas the follow-up critique.- Combine rankings: Merge your assessment with Gemini's ranking. Select top 2-3 ideas for pilot experiments.
Phase 5: Parallel Pilot Experiments (for top 2-3 ideas)
Before committing to a full research effort, run cheap pilot experiments to get empirical signal. This is the key differentiator from paper-only validation.
- Design pilots: For each top idea, define the minimal experiment that would give a positive or negative signal:
- Single seed, small scale (e.g., small dataset subset, fewer epochs)
- Target: 30 min - PILOT_MAX_HOURS per pilot on 1 GPU
- Estimate GPU-hours BEFORE launching. If estimated time > PILOT_MAX_HOURS, reduce scale (fewer epochs, smaller subset) or flag as "needs manual pilot"
- Clear success metric defined upfront (e.g., "if metric improves by > 1%, signal is positive")
- Deploy in parallel: Use
/run-experimentto launch pilots on different GPUs simultaneously:
UseGPU 0: Pilot for Idea 1 GPU 1: Pilot for Idea 2 GPU 2: Pilot for Idea 3run_in_background: trueto launch all at once. - Collect results: Use
/monitor-experimentto check progress. If any pilot exceeds PILOT_TIMEOUT_HOURS, kill it and collect partial results. Once all pilots complete (or timeout), compare:- Which ideas showed positive signal?
- Which showed null/negative results? (eliminate or deprioritize)
- Any surprising findings that suggest a pivot?
- Total GPU-hours consumed (track against MAX_TOTAL_GPU_HOURS budget)
- Re-rank based on empirical evidence: Update the idea ranking using pilot results. An idea with strong pilot signal jumps ahead of a theoretically appealing but untested idea.
Note: Skip this phase if the ideas are purely theoretical or if no GPU is available. Flag skipped ideas as "needs pilot validation" in the report.
Phase 6: Output — Ranked Idea Report
Write a structured report to idea-stage/IDEA_REPORT.md:
# Research Idea Report
**Direction**: [user's research direction]
**Generated**: [date]
**Ideas evaluated**: X generated → Y survived filtering → Z piloted → W recommended
## Landscape Summary
[3-5 paragraphs on the current state of the field]
## Recommended Ideas (ranked)
### Idea 1: [title]
- **Hypothesis**: [one sentence]
- **Reference-led provenance**: [candidate ID + source locators, or none]
- **Evidence gate**: [source status + evidence still required]
- **Conclusion boundary**: [strongest supported claim and excluded claim]
- **Minimum experiment**: [concrete description]
- **Expected outcome**: [what success/failure looks like]
- **Novelty**: X/10 — closest work: [paper]
- **Feasibility**: [compute, data, implementation estimates]
- **Risk**: LOW/MEDIUM/HIGH
- **Paper type**: method-primary / audit-support / audit-only
- **Method delta**: the smallest implementable change to a named step
- **Pilot result**: [POSITIVE: metric +X% / NEGATIVE: no signal / SKIPPED: needs GPU]
- **Reviewer's likely objection**: [strongest counterargument]
- **Why we should do this**: [1-2 sentences]
### Idea 2: [title]
...
## Eliminated Ideas (for reference)
| Idea | Reason eliminated |
|------|-------------------|
| ... | Already done by [paper] |
| ... | Requires > 1 week GPU time |
| ... | Result wouldn't be interesting either way |
## Pilot Experiment Results
| Idea | GPU | Time | Key Metric | Signal |
|------|-----|------|------------|--------|
| Idea 1 | GPU 0 | 45 min | +2.3% CE | POSITIVE |
| Idea 2 | GPU 1 | 30 min | -0.1% CE | NEGATIVE |
| Idea 3 | GPU 2 | 1.5 hr | +0.8% CE | WEAK POSITIVE |
## Suggested Execution Order
1. Start with Idea 1 (positive pilot signal, lowest risk)
2. Idea 3 as backup (weak signal, may need larger scale to confirm)
3. Idea 2 eliminated by pilot — negative result documented
## Next Steps
- [ ] Scale up Idea 1 to full experiment (multi-seed, full dataset)
- [ ] If confirmed, invoke /auto-review-loop for full iterationOutput Protocols
Follow these shared protocols for all output files:
- Output Versioning Protocol — write timestamped file first, then copy to fixed name
- Output Manifest Protocol — log every output to docs/project/OUTPUT_MANIFEST.md
- Output Language Protocol — respect the project's language setting
Key Rules
- Large file handling: If the Write tool fails due to file size, immediately retry using Bash (
cat << 'EOF' > file) to write in chunks. Do NOT ask the user for permission — just do it silently. - The user provides a DIRECTION, not an idea. Your job is to generate the ideas.
- Quantity first, quality second: brainstorm broadly, then filter ruthlessly.
- A good negative result is just as publishable as a positive one. Prioritize ideas where the answer matters regardless of direction.
- Don't fall in love with any idea before validating it. Be willing to kill ideas.
- Always estimate compute cost. An idea that needs 1000 GPU-hours is not actionable for most researchers.
- "Apply X to Y" is the lowest form of research idea. Push for deeper questions.
- Include eliminated ideas in the report — they save future time by documenting dead ends.
- If the user's direction is too broad (e.g., "NLP", "computer vision", "reinforcement learning"), STOP and ask them to narrow it. A good direction is 1-2 sentences specifying the problem, domain, and constraint — e.g., "factorized gap in discrete diffusion LMs" or "sample efficiency of offline RL with image observations". Without sufficient specificity, generated ideas will be too vague to run experiments on.
Composing with Other Skills
After this skill produces the ranked report:
/idea-creator "direction" → ranked ideas
/novelty-check "top idea" → deep novelty verification (already done in Phase 4, but user can re-run)
/research-review "top idea" → external critical feedback
implement → write code
/run-experiment → deploy to GPU
/auto-review-loop → iterate until submission-readyDoes 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.

