AGENT SKILL

positive-control

Distinguish a failed subject from a broken verification path. Use before relying on search or grep output, logs, composed prompts, stored artifacts, or before/after measurements to support a verdict.

License 许可
MIT
所属仓库
muratovv/ai-hats
最近更新
2026-11-05
Stars
★ 3
Forks
1

01 前言 Front Matter

name
positive-control
license
MIT
description
Distinguish a failed subject from a broken verification path. Use before relying on search or grep output, logs, composed prompts, stored artifacts, or before/after measurements to support a verdict.

03 SKILL.md 正文

Positive Control

Separate subject failure from verification-path failure before issuing a verdict.

When to Use

This complements exit-code provenance: it validates the evidence path, not process success. Put deterministic controls in tests; use this protocol when selecting a sensitive control requires judgment.

Procedure

  1. State the subject claim before the check.
  2. Choose a known-outcome control that traverses the same path and would fail under the likely verifier fault.
  3. Run the control before interpreting the subject.
  4. If it fails, the method is invalid: repair it and rerun both checks. Issue no subject verdict.
  5. If it passes, a subject failure belongs to the subject; a pass is usable evidence for the claim.
  6. Before a delta, establish each input's intended source identity.

Completion

  • Report the subject, control, both outcomes, and provenance; a failed control leaves no subject verdict.
  • Validation — case 3: RED compares a missing baseline with the current tree and falsely reports zero delta. GREEN checks each component's intended root; the baseline control fails, so the agent withholds the delta verdict.

Anti-Patterns

  • Another parser, source, or normalization path isolates nothing; use the subject's exact path.
  • An insensitive control can pass on wrong or empty input; choose one that detects the suspected fault.
  • Success or zero delta without provenance is ambiguous; establish identity.

04 同仓库更多 Skills

muratovv
muratovv/ai-hats

tool-evaluation-protocol

Time-bounded protocol for evaluating new tools, libraries, or methodologies before adoption. Use when evaluating a candidate dependency for the project, researching a methodology (e.g. ML/LLM frameworks, testing approaches), or following up on a hype-driven recommendation.

★ 3
muratovv
muratovv/ai-hats

systematic-debugging

4-phase bug-fix protocol (evidence, pattern, hypothesis, verify). Use when investigating any error, failure, or unexpected behavior, handling bug reports from users or monitoring, or diagnosing test failures with non-obvious causes.

★ 3
muratovv
muratovv/ai-hats

skill-template

Canonical template and validation guide for ai-hats skills. Use when creating a new skill, reviewing an existing one for structural compliance, or deciding which pattern fits a new behavior.

Skill与智能体开发
★ 3
muratovv
muratovv/ai-hats

skill-optimization

Audit and refactor library components to eliminate redundancy and staleness. Use during periodic library maintenance, after adding multiple new skills or rules, when a role's token budget is too high, or after retrospectives identify component issues.

Skill与智能体开发
★ 3
muratovv
muratovv/ai-hats

silent-fallback-gate

PreToolUse hook — refuses an Edit or Write that adds an inert broad except. Use when a Python edit was blocked for a silent fallback.

★ 3
muratovv
muratovv/ai-hats

retro-to-framework

Convert an observation about agent behavior — from a retrospective or from a single incident — into a framework-level change (hook, rule, skill, skill update). Use after a retrospective identifies problems that are not project-specific, after an incident where an agent misapplied a component it had read, when CLAUDE.md band-aids accumulate (more than 3 per-project rules that could be generic), or when the same problem recurs across multiple projects.

Skill与智能体开发
★ 3