verification-baseline
Use after applying a candidate change to verify its diff, scope, syntax, integration behavior, and consistency before returning it.
- License 许可
- MIT
- 最近更新
- 2026-11-04
- Stars
- ★ 251
- Forks
- 21
01 前言 Front Matter
- name
- verification-baseline
- description
- Use after applying a candidate change to verify its diff, scope, syntax, integration behavior, and consistency before returning it.
02 资源文件 2
- 参考文档references/asset-rights.md802 B
- 参考文档references/identity.md1.7 KB
03 SKILL.md 正文
Verification Baseline (Core)
Purpose (Core)
Verification asks whether the complete candidate is internally consistent, loadable, within scope, and capable of producing the intended effect without obvious collateral damage. It is not permission to weaken the intended change until a check passes.
Procedure (Core)
Before returning a change:
- Review the complete diff or update set. Remove unintended edits, debug text, stale artifacts, no-op churn, and unrelated formatting.
- Confirm every changed unit is inside the declared mutation scope, every declared unit actually changed, and every protected input is untouched.
- Trace dependencies and callers of shared surfaces. Preserve registration, imports, defaults, signatures, schemas, side effects, and companion files unless the diagnosis requires a coordinated change.
- Validate syntax and structure with the plugin's available checks. Confirm the candidate loads through its real integration path, not only an isolated parser.
- Inspect the final rendered or agent-visible form of prompts, descriptions, templates, hooks, and schemas. Check placeholders, escaping, formatting, examples, parameter names, and runtime behavior for consistency.
- Exercise empty inputs, boundary values, error paths, and representative existing callers when they can reach the changed surface.
- Recheck behavior that already passed and could be affected. A targeted fix should not silently broaden, suppress, or reorder unrelated behavior.
- Confirm the mutation is substantive: the effective candidate differs in the intended way after normalization, rendering, or serialization.
- Return only when the proposed effect, actual changed units, verification evidence, and structured result agree exactly.
Failure Handling (Core)
If verification fails, repair or remove the invalid change and rerun the same check. Do not hide the failure, modify protected evaluation logic, fabricate a successful result, or change intended semantics merely to satisfy a superficial check. The plugin-specific verification skill may impose stricter rules; those rules are part of the candidate contract.
04 同仓库更多 Skills
history-analysis
Use to systematically analyze the full evolution history without output truncation and produce a focused summary for selection, diagnosis, or reflection.
causal-diagnosis
Use before proposing a mutation to diagnose measured failures from evaluator outcomes, traces, history, and the controlling candidate surfaces.
steering-patch
Selected during the steering phase to refine agent behavior through prompts, tool descriptions, or hook reminders without changing executable code.
patch-verification
Use after applying a Meta-ARE patch to check syntax, imports, integration behavior, hooks, mutation scope, and result consistency.
capability-patch
Selected during the capability phase to add tools, expose parameters, fix implementations, or remove infrastructure limitations that restrict the agent.
steering-patch
Selected during the steering phase — refines agent behavior by modifying prompts, tool descriptions, or hook reminders without changing executable code