AugmentClaude

Academic Experiments

Audit and verify experimental evidence for research papers with reproducibility checks.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/academic-experiments-joshua-zyy/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

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.

What this skill does

Academic Experiments

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。

Router Protocol

  1. Read manifest.yaml. It declares always_load files, axes, and references.on_demand.
  2. Read every file listed under always_load. These are the skill's binding rules — not reference material.
  3. Apply the loaded material as constraints:
    • 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.
  4. Detect the mode using the manifest's mode axis: experiment-evidence-pass, evidence-inventory-only, or minimal-reproducible-run. Align evidence type semantics to ../shared/core/evidence-policy.md.
  5. Echo the selected mode to the user before executing.
  6. Reach for references/ only when the manifest's references.on_demand condition is satisfied.

Modes

ModeUse when
experiment-evidence-passFull audit: inventory + run + record + risk analysis
evidence-inventory-onlyInventory existing artifacts only, no execution
minimal-reproducible-runExecute minimal reproducible command (e.g. eval existing checkpoint)

Agent Dispatch

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.

Independent Use

InputModePriorityBehavior
repo_path + no run modeexperiment-evidence-pass2 (path trigger)Full audit: inventory → env → minimal run → risk
repo_path + "inspect only"evidence-inventory-only1 (explicit)Inventory only, no commands
repo_path + specific commandminimal-reproducible-run1 (explicit)Verify env → execute → record
No repo_path3 (no input)Ask path, or auto-detect entry files
ScenarioRecommended
Just auditing/reproducing evidenceThis skill (standalone)
Writing results into paper proseacademic-paper-writer orchestrator
Draft results need verificationThis skill → academic-reviser

Related skills