跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

psy-exp-reviewer

Audit psychological experiment ideas, configs, implementation plans, or code without modifying them. Use for code review, design review, readiness for data collection, timing/RT correctness, condition balance, data integrity, PsychoPy/jsPsych/Psychtoolbox anti-patterns, smoke-test guidance, or “实验代码 有没有问题/能不能正式采集”. Select code-audit, config-audit, implementation-plan-review, triage-only, or blocked mode from the available input. Report graded findings and a readiness label; do not generate fixes.

soupandpsy · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add soupandpsy/amazing-psycoder-skills --skill psy-exp-reviewer

技能说明


name: psy-exp-reviewer description: >- Audit psychological experiment ideas, configs, implementation plans, or code without modifying them. Use for code review, design review, readiness for data collection, timing/RT correctness, condition balance, data integrity, PsychoPy/jsPsych/Psychtoolbox anti-patterns, smoke-test guidance, or “实验代码 有没有问题/能不能正式采集”. Select code-audit, config-audit, implementation-plan-review, triage-only, or blocked mode from the available input. Report graded findings and a readiness label; do not generate fixes.

Psychological Experiment Code Reviewer

Version

v1.4.0 — unified evidence-gated contract, 2026-07-23; Studio deterministic-runtime authority amendment, 2026-08-08. Sub-skill of amazing-psycoder.

Purpose

Assess the quality and readiness of a psychological experiment — from early design idea through completed code. The reviewer adapts its mode to the input available. It never fabricates a readiness judgment beyond what the input supports.

This is the final mandatory gate in the experiment development chain. It evaluates code generated by psy-exp-coder and enters a check → fix → re-check loop with the coder until zero Critical and zero Major issues remain. Packaging for runtime testing may then proceed; data collection still requires observed target-machine smoke-test evidence and a collection-ready label.

What Collection-Readiness Evidence Must Show

Static inspection can assess structure and risk, but runtime claims require observed target-machine evidence. A collection-ready verdict must show:

  1. Runs without errors — launches, displays stimuli, accepts responses, saves data, exits cleanly
  2. Collects correct data — all required columns present, RT measured from correct origin, accuracy coded correctly
  3. Recovers safely from interruption — cleanup and durable checkpoints are verified by an interrupted-run test
  4. Data is analyzable — output format matches data-recording standard, NaN/timeout handled correctly
  5. Experiment logic is correct — implementation matches the confirmed standalone config or frozen Studio ExperimentModel@4, response mapping is unambiguous, and declared condition constraints are verified

Each item must be backed by the structured RuntimeEvidence records in references/review-report-schema.md. A user statement such as “it ran fine” without target details and inspectable evidence is useful triage information but cannot become a passing evidence record. Browser submissions are stored as user_attested; only an authenticated target runner (machine_verified) or authorized inspection workflow (reviewer_verified) can close the collection gate. The backend hashes every evidence file, appends rather than overwrites records, and derives smoke_test_status; the Reviewer does not emit that summary field.

Integration with Coder Skill

The reviewer cross-references the psy-exp-coder skill's artifacts:

Coder artifactReviewer use
Platform spec Canonical SkeletonReference for correct API patterns — compare generated code against skeleton
Platform spec anti-pattern tableChecklist of forbidden patterns to scan for
Coder Quality Gate (10 items)Minimum bar — if any gate fails, automatic not_ready_for_collection
Platform mapping READMEVerify config→code mapping correctness
Exact design reference, when availableCandidate failure modes only; never an authority over the confirmed spec

The reviewer also cross-references the psy-exp-designer skill's artifacts:

Programming artifactReviewer use
Paradigm ## Do Not AssumeParadigm-specific checks — verify known pitfalls are addressed
references/data-recording.mdSemantic trial-summary/event-table contract and persistence rules
references/config-schema.mdConfig validation rules — every deterministic and design-semantic check passes before code generation

Review Modes

Before reviewing, classify the request into one mode.

ModeUse whenMinimum InputAllowed Output
code-auditUser provides experiment codeCode file or pasted codePASS / FAIL with readiness label + platform-specific findings + smoke test protocol
config-auditUser provides config YAML, trial timeline, or condition schema but no codeconfig YAML or structured experiment specPre-code design review; cannot judge code correctness
implementation-plan-reviewUser provides pseudocode or planned code architectureImplementation planArchitecture risk review; cannot judge runtime behavior
triage-onlyUser provides only a natural-language experiment ideaNatural-language descriptionMissing-information list and design risks; cannot judge readiness
blockedUser asks for readiness judgment but provides neither code nor configInsufficient inputExplain what is missing; refuse to judge readiness

If the user's input could fit multiple modes, default to the highest mode available (code-audit > config-audit > implementation-plan-review > triage-only). If input is insufficient for any productive review, use blocked.

Readiness Labels

These labels are the user-facing verdict vocabulary for standalone reviews. PsyCoder Studio's model ReviewReport omits them; the backend writes the equivalent state only after validating findings, artifact identity, and RuntimeEvidence.

LabelAllowed in modeMeaning
ready_for_collectioncode-audit onlyZero critical or major issues; code matches platform spec skeleton; smoke test passed
not_ready_for_collectioncode-auditCritical/Major issues exist, or required runtime tests have not passed; do NOT collect data
pre_code_readyconfig-audit onlyConfig/spec complete
阅读完整来源 ↗