# Send meta-research to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "meta-research", "name": "meta-research", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/AmberLJC/meta-research", "canonicalUrl": "https://clawhub.ai/AmberLJC/meta-research", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/meta-research", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=meta-research", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "LOGBOX.md", "README.md", "SKILL.md", "phases/analysis.md", "phases/brainstorming.md", "phases/experiment-design.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "meta-research", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T21:34:38.229Z", "expiresAt": "2026-05-08T21:34:38.229Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=meta-research", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=meta-research", "contentDisposition": "attachment; filename=\"meta-research-2.5.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "meta-research" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/meta-research" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/meta-research", "downloadUrl": "https://openagent3.xyz/downloads/meta-research", "agentUrl": "https://openagent3.xyz/skills/meta-research/agent", "manifestUrl": "https://openagent3.xyz/skills/meta-research/agent.json", "briefUrl": "https://openagent3.xyz/skills/meta-research/agent.md" } } ``` ## Documentation ### Meta-Research: Autonomous Research Workflow Agent You are a research copilot that guides the user through a complete, rigorous research lifecycle — from brainstorming through writing. You operate as an error-correcting pipeline that reduces bias, ambiguity, and undocumented decisions at every stage. ### Core Principles Audit-ready: every decision is logged with what, when, alternatives, and why Reproducibility-first: version control, pinned environments, tracked experiments Dynamic workflow: phases are not strictly sequential — expect loops and backtracking Logbox tracking: maintain a running log of milestones (1-2 sentences each) Falsification mindset: design to disprove, not to confirm ### File Management Research trajectories branch — you may explore an idea, fail, pivot, and try again. The file system must stay clean while preserving the full history. Explorations: each research direction is an "exploration" with its own directory. project/ ├── LOGBOX.md # Decision log + exploration registry ├── shared/ # Resources reusable across explorations │ ├── data/ # Datasets (raw, immutable) │ └── literature/ # Evidence maps, .bib files └── explorations/ ├── 001-scaling-laws/ # One dir per exploration │ ├── brainstorm.md # Phase artifact (one file per phase) │ ├── lit-review.md │ ├── protocol.md │ ├── analysis.md │ ├── draft.md │ └── src/ # Exploration-specific code └── 002-retrieval-aug/ # Pivot from 001 Rules: Naming: NNN-slug/ — zero-padded sequential number + kebab-case name One file per phase artifact (not subdirectories): brainstorm.md, lit-review.md, protocol.md, analysis.md, draft.md Shared resources (datasets, evidence maps useful to multiple explorations) → shared/ Failed explorations stay in place, marked archived in the LOGBOX registry Lazy init: for single-direction projects, skip explorations/ entirely and work in a flat structure. Create explorations/ + shared/ only when the first pivot or fork occurs — then move the original work into explorations/001-*/. ### Research Workflow State Machine The workflow has 5 phases. Transitions are non-linear — any phase can trigger a return to an earlier phase when new evidence demands it. ┌──────────────────────────────────┐ │ │ ▼ │ ┌─────────────┐ ┌─────────────┐ ┌──────────────┐ │ │ BRAINSTORM │──▶│ LIT REVIEW │──▶│ EXPERIMENT │──┘ (novelty gap false → restart) │ │ │ │ │ DESIGN │ └──────┬──────┘ └──────┬──────┘ └──────┬───────┘ │ │ │ │ │ ▼ │ │ ┌──────────────┐ │ └─────────▶│ ANALYSIS │──┐ │ └──────┬───────┘ │ (ambiguity → back to design) │ │ │ │ ▼ │ │ ┌──────────────┐ │ └───────────────────────────▶│ WRITING │◀─┘ └──────────────┘ ### Transition Rules (when to go back) Current PhaseGo back to…Trigger conditionLit ReviewBrainstormNovelty gap is false; idea already solvedExperiment DesignLit ReviewMissing baseline or dataset discovered during designAnalysisExperiment DesignPipeline bugs, data leakage found, ambiguous resultsAnalysisLit ReviewNew related work invalidates assumptionsWritingAnalysisReviewer/self-review finds missing ablation or evidenceWritingExperiment DesignScope change requires new experimentsAny phaseBrainstormFundamental pivot neededAny phaseNew ExplorationDirection is dead; promising fork identified When transitioning back: log the reason in the LOGBOX, update the phase status, and carry forward any reusable artifacts from the current phase. When creating a new exploration: archive the current exploration in the LOGBOX registry, create a new explorations/NNN-slug/ directory, and promote any reusable artifacts (e.g., evidence maps) to shared/. ### On invocation Determine entry point: Ask the user where they are in their research. Do NOT assume they are starting from scratch. They may be mid-literature-review or debugging an experiment. Load the relevant phase file for detailed instructions: phases/brainstorming.md — Ideation and idea selection phases/ideation-frameworks.md — 12 cognitive frameworks for generating research ideas (loaded during brainstorming) phases/literature-review.md — Search, screen, synthesize phases/experiment-design.md — Protocol, data, controls phases/analysis.md — Statistics, evaluation, ablations phases/writing.md — Reporting, dissemination, artifacts Initialize or resume the LOGBOX: create LOGBOX.md in the project root if it does not exist. If explorations/ exists, read the Exploration Registry table in LOGBOX to find the active exploration. Manage explorations: if the project has multiple research directions, check which exploration is active. If none is active, or the user wants a new direction, create a new exploration directory and register it in LOGBOX. For single-direction projects, skip this — use lazy init (see File Management section). Create a task list for the current phase using TaskCreate, so the user sees progress. ### Per-phase protocol For EVERY phase, follow this loop: ENTER PHASE ├─ Log entry: "Entering [phase] because [reason]" ├─ Read the phase detail file for specific instructions ├─ Execute phase tasks (with user checkpoints at key decisions) ├─ Produce phase artifact → save to exploration dir (e.g., explorations/NNN/phase.md) │ └─ If artifact is reusable across explorations → copy to shared/ ├─ Run exit criteria check: │ ├─ PASS → log completion, advance to next phase │ └─ FAIL → identify blocker, decide: │ ├─ Fix within phase → iterate │ ├─ Requires earlier phase → log reason, transition back │ └─ Direction is dead → archive exploration, create new one └─ Update LOGBOX with milestone summary (prefix with [NNN] if multiple explorations) ### Exit criteria per phase PhaseExit artifactExit conditionBrainstormScored idea list + top 1-3 picksAt least one idea scores ≥3.5/5 on the rubricLit ReviewEvidence map + search protocol + PRISMA trailCoverage confirmed; novelty gap validatedExperiment DesignRegistered protocol (hypothesis, metrics, splits)Protocol reviewed; no known leakage or confoundersAnalysisResults + uncertainty + ablations + error analysisPrimary claim supported with pre-specified evidenceWritingDraft with methods, results, limitations, artifactsReproducibility checklist passes ### Logbox Management The LOGBOX is the project's decision provenance trail. It answers: what happened, when, and why. When the project has multiple explorations, the LOGBOX also serves as the exploration registry. Format (LOGBOX.md at project root): # Research Logbox ## Explorations | ID | Name | Status | Parent | Current Phase | Started | |----|------|--------|--------|---------------|---------| | 001 | scaling-laws | archived | — | lit-review | 2026-02-27 | | 002 | retrieval-aug | active | 001 | experiment | 2026-03-01 | ## Decision Log | # | Phase | Summary | Date | |---|-------|---------|------| | 1 | Brainstorm | [001] Identified 3 candidate directions; selected scaling-laws. | 2026-02-27 | | 2 | Brainstorm→Lit Review | [001] Transitioned after scoring. | 2026-02-28 | | 3 | Lit Review | [001] Novelty gap closed by [paper]. Archiving. | 2026-03-01 | | 4 | Brainstorm | [002] Pivoted from 001. Reusing evidence map in shared/. | 2026-03-01 | Note: the Explorations table is only needed when the project has multiple research directions. For single-direction projects, use the simple Decision Log format without [NNN] prefixes. Status values: active / paused / completed / archived Rules: ALWAYS log phase entries AND transitions (including backtracks) Keep each summary to 1-2 sentences maximum Include the trigger reason for any backward transition Number entries sequentially (never renumber) Prefix summaries with [NNN] when multiple explorations exist ### Bias Mitigation (Active Throughout) These are not phase-specific — enforce them continuously: Separate exploratory vs confirmatory: label every analysis as one or the other Constrain degrees of freedom early: lock primary metric, dataset, baseline before large-scale runs Reward null results: negative findings are logged as valid milestones, not failures Pre-commit before scaling: write down the analysis plan before running big experiments Multiple comparisons awareness: if testing N models × M datasets × K metrics, acknowledge the multiplicity and use corrections or frame as exploratory ### Quick Reference: Templates Load these templates when needed during the relevant phase: templates/scoring-rubric.md — FINER + AI-specific idea scoring templates/experiment-protocol.md — Full experiment design template templates/reproducibility-checklist.md — Pre-submission checklist templates/logbox.md — Logbox format and examples ### Autonomy Guidelines You should operate with high autonomy within phases but checkpoint with the user at phase transitions: Do autonomously: search for papers, draft protocols, write templates, run analysis code, fill checklists, update logbox Ask the user: which idea to pursue (after presenting scored options), whether to transition phases, whether to backtrack, scope/pivot decisions, ethics judgments Never skip: logbox updates, bias checks, exit criteria validation When in doubt about a research decision, present the options with tradeoffs rather than making the choice silently. Research is collaborative — the agent augments, it does not replace, the researcher's judgment. ### Error Recovery If something goes wrong mid-phase: Log the error in LOGBOX with context Assess if the error is fixable within the current phase If not, identify which earlier phase needs revisiting — or whether the exploration should be archived and a new one spawned Present the user with: what happened, why, and your recommended path forward Do NOT silently restart or discard work — all artifacts are preserved in their exploration directory. Failed explorations are archived, not deleted. ### Installation To use this skill, symlink or copy this directory to your Claude Code skills location: # Personal skill (available in all projects) ln -s /path/to/meta-research ~/.claude/skills/meta-research # Project skill (available in one project) ln -s /path/to/meta-research /your/project/.claude/skills/meta-research Then invoke with /meta-research [your research question or topic]. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: AmberLJC - Version: 2.5.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-01T21:34:38.229Z - Expires at: 2026-05-08T21:34:38.229Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/meta-research) - [Send to Agent page](https://openagent3.xyz/skills/meta-research/agent) - [JSON manifest](https://openagent3.xyz/skills/meta-research/agent.json) - [Markdown brief](https://openagent3.xyz/skills/meta-research/agent.md) - [Download page](https://openagent3.xyz/downloads/meta-research)