菜单
Skill for iterative experiment design using REVISE tasks and calibration workflows. Use when a pilot experiment fails calibration or results are unexpected and need systematic revision with full context carry-forward.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Skill for using Beads (bd) as the single source of truth for task tracking, dependency management, and agent coordination. Covers all bd commands needed for multi-agent orchestration.
Skill for working with artifact contracts — the file-level dependency system that prevents pipeline failures by ensuring tasks produce expected outputs and only start when required inputs exist.
Skill for generating scientific figures from experimental data. Ensures every figure referenced in LaTeX documents exists on disk before compilation, preventing blank PDFs and broken references.
Complete recipe for dispatching, monitoring, merging, and cleaning up worker agents. Read this skill BEFORE dispatching any worker. Covers build_worker_prompt, spawn-agent.sh, merge-agent.sh, checkpoint updates, and common failure modes.
Use when asked to reduce code complexity, simplify code, refactor safely, merge micro-files, remove dead code, shrink functions, reduce coupling, clean modules, or improve maintainability in src/voronoi/.
Use for adversarial review of Voronoi plans, findings, claims, manuscripts, and final deliverables. Covers reviewer-style objections, confounds, alternative explanations, evidence gaps, and falsification-oriented critique.
| name | revise-calibration |
| description | Skill for iterative experiment design using REVISE tasks and calibration workflows. Use when a pilot experiment fails calibration or results are unexpected and need systematic revision with full context carry-forward. |
| user-invocable | true |
| disable-model-invocation | false |
Use this skill when a pilot experiment fails calibration or produces unexpected results. REVISE tasks carry forward context from the previous attempt so the next worker doesn't repeat the same mistakes.
When a pilot experiment fails calibration or results are unexpected, create a REVISE task instead of a fresh task:
bd create "REVISE: <description>" -t task -p 1 --json
bd update <id> --notes "REVISE_OF:<previous-task-id>"
bd update <id> --notes "PRIOR_RESULT:<what happened>"
bd update <id> --notes "FAILURE_DIAGNOSIS:<why it failed>"
bd update <id> --notes "REVISED_PARAMS:<what changed>"
The worker receiving a REVISE task gets the full context of what was tried and why it failed. Include ALL revise context in the worker prompt.
CALIBRATION_ITER:N in Beads notesCALIBRATION_ESCALATED in Beads. Do NOT continue tweaking.