parity-probe

GitHub

通过普通任务板运行代表性能力冒烟测试,验证 lane、adapter 等变更后的功能正常性。要求执行实际 CLI/MCP 操作及负向检查,严格依据回执和产物判定结果,确保安全性与准确性。

plugins/chrono-vault/skills/parity-probe/SKILL.md mtarcure/claude-vibe-squad

Trigger Scenarios

lane 变更后 adapter 变更后 native-CLI 变更后 utility-MCP 变更后

Install

npx skills add mtarcure/claude-vibe-squad --skill parity-probe -g -y
More Options

Non-standard path

npx skills add https://github.com/mtarcure/claude-vibe-squad/tree/main/plugins/chrono-vault/skills/parity-probe -g -y

Use without installing

npx skills use mtarcure/claude-vibe-squad@parity-probe

指定 Agent (Claude Code)

npx skills add mtarcure/claude-vibe-squad --skill parity-probe -a claude-code -g -y

安装 repo 全部 skill

npx skills add mtarcure/claude-vibe-squad --all -g -y

预览 repo 内 skill

npx skills add mtarcure/claude-vibe-squad --list

SKILL.md

Frontmatter
{
    "name": "parity-probe",
    "description": "Run representative capability smoke tasks through the ordinary VibeSquad board after lane, adapter, native-CLI, or utility-MCP changes."
}

Run the provider parity probe

Use the existing Markdown task board. This skill is an operator checklist, not a second runner, receipt format, or capability catalog.

Procedure

  1. Dispatch an ordinary Project or Bounty task through shared/routing.md. Never invoke a provider CLI directly from this skill.
  2. For each changed family, choose a representative specialist whose declared surface contains the capability being checked.
  3. Require the task to write its normal artifact and completion envelope. When relevant, have it execute one meaningful declared local CLI or utility MCP operation and one harmless negative check for an undeclared operation.
  4. For Kimi, keep utility MCP calls on the main lead's reviewed allowlist; native Agent children remain MCP-free.
  5. Accept the smoke result only when the normal board receipt, artifact, envelope, and focused test agree. Configuration, PATH output, or a listed tool alone is not proof that the operation worked.

Stop conditions

Stop and report the route as unproven when the task fails, the declared surface differs, the operation is denied or unavailable, or the provider requires an unapproved paid or credentialed action. Do not widen credentials, retry through another family, or bypass the board.

Keep private task output and credentials out of tracked files. Record only the concise pass/fail result and the affected family/capability in the phase evidence used for the final repository-wide audit.

Version History

  • d5262e2 Current 2026-09-11 11:52

Same Skill Collection

.agents/skills/accessible-media-authoring/SKILL.md
.agents/skills/agent-prompt-engineering/SKILL.md
.agents/skills/agentic-safety-audit/SKILL.md
.agents/skills/audio-event-map-authoring/SKILL.md
.agents/skills/auto-scaffold/SKILL.md
.agents/skills/claim-verification/SKILL.md
.agents/skills/code-reachability-audit/SKILL.md
.agents/skills/code-review-loop/SKILL.md
.agents/skills/color-theory/SKILL.md
.agents/skills/conversation-design/SKILL.md
.agents/skills/copy-refinement/SKILL.md
.agents/skills/cross-file-relationship-synthesis/SKILL.md
.agents/skills/dependency-cycle-audit/SKILL.md
.agents/skills/dependency-health-triage/SKILL.md
.agents/skills/detection-as-code/SKILL.md
.agents/skills/diff-aware-semgrep-scan/SKILL.md
.agents/skills/differential-review/SKILL.md
.agents/skills/dimensional-analysis-check/SKILL.md
.agents/skills/dual-level-retrieval/SKILL.md
.agents/skills/figma-implement-design/SKILL.md
.agents/skills/forensic-timeline-authoring/SKILL.md
.agents/skills/game-design-fundamentals/SKILL.md
.agents/skills/game-mechanics-balancing/SKILL.md
.agents/skills/head-tail/SKILL.md
.agents/skills/incident-response-runbook/SKILL.md
.agents/skills/interactive-audio-design/SKILL.md
.agents/skills/interface-ambiguity-check/SKILL.md
.agents/skills/keyword-clustering/SKILL.md
.agents/skills/knowledge-base-integration/SKILL.md
.agents/skills/layered-analysis-loop/SKILL.md
.agents/skills/level-design-patterns/SKILL.md
.agents/skills/locale-adaptation/SKILL.md
.agents/skills/narrative-structure/SKILL.md
.agents/skills/platform-compliance/SKILL.md
.agents/skills/player-engagement-psychology/SKILL.md
.agents/skills/requirements-elicitation/SKILL.md
.agents/skills/rule6-rights-gate/SKILL.md
.agents/skills/rule8-truth-gate/SKILL.md
.agents/skills/sandbox-provision-discipline/SKILL.md
.agents/skills/scope-decomposition/SKILL.md
.agents/skills/scope-estimation/SKILL.md
.agents/skills/security-ownership-map/SKILL.md
.agents/skills/security-threat-model/SKILL.md
.agents/skills/semgrep-rule-author/SKILL.md
.agents/skills/skill-description-trigger-authoring/SKILL.md
.agents/skills/sound-design-principles/SKILL.md
.agents/skills/structured-data-authoring/SKILL.md
.agents/skills/supply-chain-audit/SKILL.md
.agents/skills/take-over-resume/SKILL.md
.agents/skills/technical-seo-audit/SKILL.md

Metadata

Files
0
Version
d5262e2
Hash
a96c9b72
Indexed
2026-09-11 11:52

trang chủ - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-15 19:35
浙ICP备14020137号-1 $bản đồ khách truy cập$