⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
research-innovation-explorer
Build literature-grounded research-question candidate landscapes by collecting papers, generating A+B matrices, and dynamically reviewing combinations with traceable evidence, uncertainty, and next checks. Use when an AI agent needs to explore a field, screen research questions, compare paper combinations, inspect prior art, or prepare a provisional shortlist for researcher review.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
// README
Research Innovation Explorer
This search-first workflow turns a structured paper pool and an A+B matrix into an evidence-grounded landscape of research questions, uncertainties, and next checks for researcher review.
Why This Exists
Most research-idea workflows fail in one of three ways:
- they rely on vague intuition instead of systematic search
- they generate combinations but cannot explain why the combination matters
- they lose the evidence and uncertainty that should guide the next research decision
research-innovation-explorer is built to close those gaps with one coherent workflow:
- Search broadly and repeatedly.
- Decompose papers into reusable capabilities.
- Generate and rank candidate combinations for review.
- Check both combination directions against source evidence.
- Return a provisional candidate landscape with supporting evidence, uncertainty, and next checks.
Theory framing, experiment planning, and publication-oriented reporting remain available as explicit follow-up layers for a researcher-selected candidate.
Core Methodology
This skill is built around one explicit research-production loop:
- Collect roughly 40 relevant, high-quality papers with enough detail to support comparison.
- Build a pairwise combination matrix over those papers.
- Keep one row per unique paper pair; 40 papers produce
40 x 39 / 2 = 780rows with the current generator. - Use matrix scores to build a review queue, then examine both
A -> BandB -> Athrough focused source, prior-art, code, or benchmark checks. - Keep a provisional set of questions with evidence, contrary evidence, uncertainty, and recommended next actions.
This is the operational core of the workflow, not a side note. The point is not to wait for a single flash of inspiration. The point is to search comprehensively, force structured combination, validate aggressively, and only then keep the few ideas that survive contact with evidence.
| Stage | What to do | What comes out |
|---|---|---|
| Paper pool | Gather around 40 relevant papers with reproducible detail | a reusable capability inventory |
| Combination pass | Enumerate every unique paper pair | 780 pair rows for a 40-paper pool |
| Post-matrix review | Check both directions, inspect evidence, and identify the highest-value unresolved question | candidate review records |
| Provisional landscape | Group promising, unresolved, parked, weak, and excluded candidates with reasons | a researcher-ready shortlist |
What You Get
| Layer | What it does |
|---|---|
SKILL.md | Defines the default exploration workflow, evidence rules, and optional expansion paths |
scripts/build_search_queries.py | Generates structured query packs for topic scan, novelty checks, and failure analysis |
scripts/build_idea_matrix.py | Builds a scored pairwise candidate matrix from the paper pool |
scripts/build_research_figures.py | Generates publication-style literature heatmaps, scoring heatmaps, and analysis panels from the research artifacts |
scripts/build_markdown_report.py | Scaffolds a Markdown matrix overview; reviewed evidence is added afterward |
references/ | Contains the search playbook, theory framing rules, reporting rules, and ethics boundaries |
assets/templates/ | Provides CSV, candidate-review, idea-brief, experiment-plan, and report templates |
Workflow
flowchart LR
A[Search Pass] --> B[Paper Pool]
B --> C[Capability Decomposition]
C --> D[Idea Matrix]
D --> E[Review Queue]
E --> F[Evidence Review]
F --> G[Candidate Landscape]
G -. on request .-> H[Theory Framing]
G -. on request .-> I[Experiment Plan]
G -. on request .-> J[Extended Report]
Design Principles
1. Search First
The skill assumes that current literature claims should not come from memory alone when search is available.
2. Dynamic Review
Each review round targets the uncertainty most likely to change the recommendation. Unknown, incomplete, and conflicting evidence remain visible in the output.
3. Evidence-Carrying Reports
The default candidate landscape includes:
- citations
- observed facts and agent inferences kept separate
- candidate comparison
- uncertainty and next checks
Matrix scores are triage signals. They do not establish novelty, feasibility, publishability, or expected research success.
4. Host Neutrality
The workflow is portable across different agent hosts and even manual use. The repo does not depend on one specific runtime.
Quick Start
1. Prepare the search pack
python scripts/build_search_queries.py \
--topic "long-context reasoning" \
--keywords "memory routing, verifier head, benchmark"
2. Build the paper pool
Start from:
assets/templates/search-log.csvassets/templates/paper-pool.csv
3. Generate the idea matrix
python scripts/build_idea_matrix.py \
assets/templates/paper-pool.csv \
--output work/idea-matrix.csv
4. Review candidates and optionally generate a report
After generating the matrix, copy assets/templates/candidate-review.yaml for candidates in the review queue. Read references/post-matrix-review.md and record source-linked facts, inferences, status, confidence, and next checks.
The report script remains available as a matrix-overview scaffold. Generate static figures and a Markdown overview only when they help the current review:
Generate static figures first when the final research output should include academic paper-style data visuals:
python scripts/build_research_figures.py \
--paper-pool assets/templates/paper-pool.csv \
--idea-matrix work/idea-matrix.csv \
--output-dir work/figures \
--topic "Long-Context Reasoning" \
--prefix long_context
python scripts/build_markdown_report.py \
--topic "Long-Context Reasoning" \
--paper-pool assets/templates/paper-pool.csv \
--idea-matrix work/idea-matrix.csv \
--search-log assets/templates/search-log.csv \
--figure-dir work/figures \
--figure-prefix long_context \
--output work/report.md
Optional Report Style
The reporting layer is intentionally designed for GitHub-native reading:
- Mermaid flowcharts for process explanation
- static PNG heatmaps for matrix snapshots and worked examples
- Mermaid pie charts for quick distribution views
- Markdown evidence tables for claim tracing
- compact narrative sections for executive summary and detailed analysis
This makes an optional overview readable as a working note and a shareable artifact. The default deliverable remains the provisional candidate landscape.
Example Output
Exploring LLM Training Directions
This worked example uses frontier large language model training research as the target domain. It starts from a search-backed pool of roughly 40 recent papers, builds the combination matrix, and then
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
SKILL.md5.7 KBupstream ↗
--- name: research-innovation-explorer description: Build literature-grounded research-question candidate landscapes by collecting papers, generating A+B matrices, and dynamically reviewing combinations with traceable evidence, uncertainty, and next checks. Use when an AI agent needs to explore a field, screen research questions, compare paper combinations, inspect prior art, or prepare a provisional shortlist for researcher review. --- # Research Innovation Explorer ## Purpose Help a researcher decide which literature-grounded questions deserve more attention. Search broadly, structure a paper pool, generate an A+B matrix, and review selected candidates against source evidence. Stop the default workflow at a provisional candidate landscape. Do not present matrix rankings as novelty, feasibility, publishability, or expected research success. Expand a researcher-selected candidate into theory framing, an experiment plan, or a publication-oriented report only when requested. Use this skill as a host-neutral contract. Adapt search and browsing actions to the tools available in the current environment. ## Default Workflow 1. Clarify the topic, resource constraints, available data or code, and the desired breadth of the candidate landscape. 2. Read `references/search-playbook.md`, create a working `search-log.csv`, and generate a starter query pack with `scripts/build_search_queries.py`. 3. Build a 20-50 paper pool and normalize each paper into tasks, mechanisms, strengths, weaknesses, benchmarks, and implementation signals. Read `references/workflow.md` for intake rules. 4. Run `scripts/build_idea_matrix.py` to generate `idea-matrix.csv`. The script rejects duplicate paper identifiers and orders papers by identifier so each pair has stable A/B roles. 5. Treat matrix scores only as queue-priority signals. Build the review queue from the ten highest-ranked unique pairs, up to five coverage-increasing pairs, and every researcher-requested pair. 6. Read `references/post-matrix-review.md` and `references/scoring-rubric.md`. Copy `assets/templates/candidate-review.yaml` for each candidate under review. 7. Complete both entries under `direction_checks`. Select a direction only after both `A -> B` and `B -> A` have been assessed. 8. In each review round, identify the single uncertainty most likely to change the recommendation. Perform one focused action, then update facts, inferences, the relevant direction check, decision-linked inference identifiers, status, confidence, and the next check. 9. Validate each populated review with `scripts/validate_candidate_review.py` before including it in the candidate landscape. 10. Stop when further searching mainly repeats known information, a status is adequately supported, or the next decision requires researcher input. Preserve unresolved uncertainty in the record. 11. Produce a candidate landscape using `references/reporting-and-visualization.md` and `assets/templates/analysis-report-template.md`. ## Candidate Review Rules - Verify source facts before interpreting a pairing. - Preserve the canonical `paper_a_id`, `paper_b_id`, and `candidate_id` defined by the matrix order. - Record observed facts separately from agent inferences. - Give every observed fact a stable source URL and a section, page, figure, table, or repository location. - Link every inference to the fact identifiers that support it. - Link each non-unknown direction assessment, selected direction, and decisive research status to inference identifiers. - Use `unknown` only for direction or dimension fields. Use `needs_check` or `conflicting` for research status when evidence warrants them. - Keep matrix score and qualitative review judgment separate. Do not calculate a second aggregate score. - Reopen any research judgment when new evidence changes the basis. - Stop review on broken input data and resume after the data is repaired. ## Default Deliverables - `search-log.csv` - `paper-pool.csv` - `idea-matrix.csv` - one `candidate-review.yaml` per reviewed candidate - one candidate-landscape Markdown document covering promising, unresolved, parked, weak, and excluded candidates - optional screening figures when visual comparison is useful ## Optional Expansion After the researcher selects a candidate: - read `references/framing-and-theory.md` for a framing note - read `references/experiment-plan.md` and use `assets/templates/experiment-plan.md` for a validation plan - use `scripts/build_research_figures.py` for screening visualizations - use `scripts/build_markdown_report.py` only as a matrix-overview scaffold, then add the candidate-review evidence manually Keep all claims proportional to the available evidence. Read `references/ethics-boundaries.md` whenever wording about novelty, theory, or expected results becomes stronger than the sources support. ## Resources - `references/workflow.md`: paper intake, matrix generation, queue construction, and default outputs - `references/search-playbook.md`: search objectives, source selection, logging, and stopping rules - `references/post-matrix-review.md`: dynamic review loop, evidence records, statuses, and failure handling - `references/scoring-rubric.md`: qualitative dimensions and state assignment - `references/reporting-and-visualization.md`: candidate-landscape reporting rules - `references/framing-and-theory.md`: optional framing guidance for selected candidates - `references/experiment-plan.md`: optional experiment planning guidance - `references/ethics-boundaries.md`: claim and evidence boundaries - `assets/templates/candidate-review.yaml`: stable review record interface - `assets/templates/analysis-report-template.md`: researcher-facing candidate landscape - `scripts/validate_candidate_review.py`: deterministic candidate identity and evidence-link validationREADME.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/foryourhealth111-pixel-research-innovation-explorer.md