القائمة
Use when reviewing experiment topics, run.py files, experiment registries, GPU/JAX environment ownership, notebook artifacts, or experiment README/report readiness.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when agent-side working philosophy, interaction lessons, task retrospectives, repeated routing misses, missed skill invocation, or recurrence-prevention feedback should be logged without mixing them into user preferences.
Use when exploring, refactoring, or choosing an algorithm under proof obligations; builds JIT-canonical IR, lemma dependency graphs, algorithmic blocker frontiers, and algorithm-change guidance before handing terminal proof work to formal-proof-workflow.
Use when designing, implementing, reviewing, or diagnosing numerical optimization, solvers, preconditioners, convergence, gradients, Jacobians, Hessians, KKT conditions, tolerances, or optimization benchmarks; fixes the mathematical and validation contract before code or experiment changes.
Use when a change needs oracle/spec-risk classification or resilient, adversarial static test design, including behavior contracts, oracle choice, property/metamorphic candidates, mutation adequacy, or brittle-test diagnosis.
Use when updating AgentCanon itself, refreshing a vendored vendor/agent-canon submodule pin, repairing AgentCanon root runtime views, applying AgentCanon update TODOs, or routing local AgentCanon source commits through a proper AgentCanon branch and PR before parent pin updates.
Use when accumulated AgentCanon eval evidence is missing, stale, or failing; runs registered eval producers, validates eval family accumulation, and stores evidence through the log archive instead of hand-writing reports.
| name | experiment-review |
| description | Use when reviewing experiment topics, run.py files, experiment registries, GPU/JAX environment ownership, notebook artifacts, or experiment README/report readiness. |
Use the command packet before applying this skill's workflow:
python3 tools/agent_tools/skill_tool_commands.py show --skill experiment-review --format text
Execute the required and task-matching conditional commands that the packet prints.
agents/skills/experiment-review.md.experiments/registry.toml -> topic README.md -> config.yaml -> run.py -> notebook./usr/bin/python experiments/<topic>/run.py with no CLI options is the canonical run command.max_workers: 1, or equivalent serial
throttles unless the user explicitly requested an environment-contract change.os.environ.copy() or default
inheritance instead of replacing GPU/JAX runtime settings.run.py entrypoint
directly. Confirm the direct run
writes summary.json, cases.jsonl, config snapshot, case artifacts, and
notebook output under experiments/<topic>/result/<run_name>/.run.py, environment hard-coding in topic code, or child
subprocess environment reset as fix-now findings.