Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
Audit, run, or verify experimental evidence for CS/AI/ML papers. Produces Evidence Inventory with evidence_type annotations (newly_run/preexisting_artifact/user_claim) and Protocol Risk assessments. Use when: checking if experiment results are reproducible, auditing existing experiment artifacts, running minimal reproducible commands, evaluating checkpoints without full retraining, documenting protocol risks like data leakage or missing baselines. Triggers on: 复核实验, run experiments, 实验结果, experiment evidence, verify results, 实验验证, evidence inventory, protocol risk, 跑实验, check results, reproduce experiments, 实验审计.
How this skill is triggered — by the user, by Claude, or both
Slash command
/academic-paper-writer:academic-experimentsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
将此 skill 视为"实验取证代理"，目标是建立最短且可信的证据链，而不是尽量多跑实验。
将此 skill 视为"实验取证代理"，目标是建立最短且可信的证据链，而不是尽量多跑实验。
manifest.yaml. It declares always_load files, axes, and references.on_demand.always_load. These are the skill's binding rules — not reference material.stance.md defines non-negotiable rules, evidence type semantics, failure degradation, and scope.red-lines.md defines absolute prohibitions. Do not negotiate these.output-contract.md defines deliverables per mode and claim-readiness classification.anti-patterns.md defines known failure modes and their correct alternatives.mode axis: experiment-evidence-pass, evidence-inventory-only, or minimal-reproducible-run. Align evidence type semantics to ../shared/core/evidence-policy.md.references/ only when the manifest's references.on_demand condition is satisfied.| Mode | Use when |
|---|---|
experiment-evidence-pass | Full audit: inventory + run + record + risk analysis |
evidence-inventory-only | Inventory existing artifacts only, no execution |
minimal-reproducible-run | Execute minimal reproducible command (e.g. eval existing checkpoint) |
agents/experiment_agent.md is dispatched by academic-paper-writer orchestrator at Step 4. The agent may run experiments but must not modify project source code or data files, nor write paper prose independently.
| Input | Mode | Priority | Behavior |
|---|---|---|---|
repo_path + no run mode | experiment-evidence-pass | 2 (path trigger) | Full audit: inventory → env → minimal run → risk |
repo_path + "inspect only" | evidence-inventory-only | 1 (explicit) | Inventory only, no commands |
repo_path + specific command | minimal-reproducible-run | 1 (explicit) | Verify env → execute → record |
No repo_path | — | 3 (no input) | Ask path, or auto-detect entry files |
| Scenario | Recommended |
|---|---|
| Just auditing/reproducing evidence | This skill (standalone) |
| Writing results into paper prose | academic-paper-writer orchestrator |
| Draft results need verification | This skill → academic-reviser |
npx claudepluginhub joshua-zyy/academic-paper-writerAudit the experimental **methodology** integrity for a specific claim (Checks A–F: GT provenance, score normalization, result-file existence, dead code, scope, eval-type). Uses cross-model review (external LLM reviewer via llm-chat MCP). The output `overall_verdict` (PASS/WARN/FAIL) is THIS claim's verdict — i.e., whether the claim's experimental process is methodologically sound. Does NOT judge whether the numbers semantically support the claim's hypothesis — that is `/result-to-claim`'s job.
Verifies reproducibility claims for experiments: requires exact commands, config, seed, commit hash, dataset version, and metric tables before accepting performance improvements.
Audits IJCAI/IJCAI-ECAI experiments for baselines, ablations, statistical evidence, hyperparameters, compute, dataset handling, ethics, and reproducibility.