Agent Skillsboshu2/agentops › anti-ceremony

anti-ceremony

GitHub

防止流程冗余,确保工作聚焦于最终成果。通过快速审查或全面审计,识别并暂停无实际价值的过程性工作,减少无效开销。

images/gemini/skills/anti-ceremony/SKILL.md boshu2/agentops

Trigger Scenarios

RPI 计划前的审查请求 显式的反仪式审计请求

Install

npx skills add boshu2/agentops --skill anti-ceremony -g -y
More Options

Non-standard path

npx skills add https://github.com/boshu2/agentops/tree/main/images/gemini/skills/anti-ceremony -g -y

Use without installing

npx skills use boshu2/agentops@anti-ceremony

指定 Agent (Claude Code)

npx skills add boshu2/agentops --skill anti-ceremony -a claude-code -g -y

安装 repo 全部 skill

npx skills add boshu2/agentops --all -g -y

预览 repo 内 skill

npx skills add boshu2/agentops --list

SKILL.md

Frontmatter
{
    "name": "anti-ceremony",
    "consumes": [
        "caller-outcome",
        "proposed-process-work",
        "proof-state"
    ],
    "metadata": {
        "tier": "judgment",
        "effects": [],
        "stability": "experimental",
        "disposition": "keep_specialist",
        "capabilities": [
            "guard_anti_ceremony",
            "audit_anti_ceremony"
        ],
        "dependencies": [],
        "canonical_status": "canonical"
    },
    "produces": [
        "anti-ceremony-decision"
    ],
    "practices": [
        "lean",
        "evidence-based-development"
    ],
    "context_rel": [],
    "description": "Guard outcome work against process overhead. Triggers: RPI pre-Plan guard; explicit \"full anti-ceremony audit\" requests.",
    "hexagonal_role": "supporting",
    "user-invocable": true,
    "output_contract": "artifact-free CONTINUE or STOP decision with reason, frozen_outcome, parked_process_work, remaining_proof, and stop_condition",
    "skill_api_version": 1
}

Anti-Ceremony

Keep work tied to the caller-visible outcome and the proof still needed for it. The default guard is a single, artifact-free judgment before RPI Plan.

Modes

Trigger Mode
RPI pre-Plan invocation or ordinary use Quick guard
Explicit request for a full anti-ceremony audit Full honesty audit

Never promote the quick guard into the full audit without the explicit trigger.

Quick guard

  1. Freeze the caller-visible outcome in one short statement.
  2. Park proposed process work that has no concrete consumer, gated subject or release decision, observed defect, or retirement condition.
  3. Name the implementation or independent proof still missing.
  4. Name the condition that ends this traversal.
  5. Return STOP when the traversal would only create control artifacts or the frozen outcome is already sufficiently proved; otherwise return CONTINUE.

Perform the guard exactly once in memory. Write no worksheet, ledger, capture, dashboard, prompt packet, or other hidden artifact. Parking is a field in the response, not a tracker or delivery mutation.

Return this shape:

decision: CONTINUE | STOP
reason: <exactly one sentence>
frozen_outcome: <nonempty string>
parked_process_work: [<work item>, ...]
remaining_proof: [<proof item>, ...]
stop_condition: <nonempty string>

The two lists contain strings and may be empty. Done when every field is present and the decision explains whether one RPI traversal earns its cost.

Full honesty audit

Run this mode only when the caller explicitly requests it. Examine each named control artifact or ceremony step for its consumer, gated subject or release decision, observed defect, and retirement condition. Return concise keep, park, or drop findings in the response; create no audit artifact unless the caller separately requests one.

Boundaries

The guard makes one admission judgment. It does not retry, repair, replan, dispatch core phases, operate Git or a tracker, deliver, release, or select a next action. On malformed or missing inputs, return STOP with the missing field named in the one-sentence reason and stop.

Version History

  • 7b07a7d Current 2026-08-19 21:58

Same Skill Collection

images/gemini/skills/account-rotation/SKILL.md
images/gemini/skills/agent-mail/SKILL.md
images/gemini/skills/agent-native/SKILL.md
images/gemini/skills/agy-native/SKILL.md
images/gemini/skills/automation-shape-routing/SKILL.md
images/gemini/skills/bootstrap/SKILL.md
images/gemini/skills/cass/SKILL.md
images/gemini/skills/cc-hooks/SKILL.md
images/gemini/skills/codebase-recon/SKILL.md
images/gemini/skills/codex-exec/SKILL.md
images/gemini/skills/converter/SKILL.md
images/gemini/skills/council/SKILL.md
images/gemini/skills/craft-goal/SKILL.md
images/gemini/skills/dcg/SKILL.md
images/gemini/skills/doc/SKILL.md
images/gemini/skills/domain/SKILL.md
images/gemini/skills/fitness/SKILL.md
images/gemini/skills/goals/SKILL.md
images/gemini/skills/handoff/SKILL.md
images/gemini/skills/idea-genie/SKILL.md
images/gemini/skills/implement/SKILL.md
images/gemini/skills/learn/SKILL.md
images/gemini/skills/ms/SKILL.md
images/gemini/skills/ntm/SKILL.md
images/gemini/skills/operationalize/SKILL.md
images/gemini/skills/pattern-mining/SKILL.md
images/gemini/skills/plan/SKILL.md
images/gemini/skills/postmortem/SKILL.md
images/gemini/skills/premortem/SKILL.md
images/gemini/skills/product/SKILL.md
images/gemini/skills/rch/SKILL.md
images/gemini/skills/reality-check/SKILL.md
images/gemini/skills/refactor/SKILL.md
images/gemini/skills/research/SKILL.md
images/gemini/skills/reverse-engineer/SKILL.md
images/gemini/skills/rpi/SKILL.md
images/gemini/skills/sbh/SKILL.md
images/gemini/skills/scaffold/SKILL.md
images/gemini/skills/scope/SKILL.md
images/gemini/skills/security/SKILL.md
images/gemini/skills/shared/SKILL.md
images/gemini/skills/skill-builder/SKILL.md
images/gemini/skills/standards/SKILL.md
images/gemini/skills/status/SKILL.md
images/gemini/skills/swarm/SKILL.md
images/gemini/skills/test/SKILL.md
images/gemini/skills/toil-mining/SKILL.md
images/gemini/skills/using-flywheel/SKILL.md
images/gemini/skills/using-gc/SKILL.md

Metadata

Files
0
Version
7b07a7d
Hash
c10d2b26
Indexed
2026-08-19 21:58

inicio - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-20 00:38
浙ICP备14020137号-1 $mapa de visitantes$