Geruyang/GAS-Agent-Skills / GAS-Agent-Skills/gas-decentralized-development
gas-decentralized-development
VerifiedUse when a user requests 分权模式, 分权开发模式技能, 工程开发中的三权分立, separation-of-powers development, or peer agents with separate rulemaking, execution, and adjudication responsibilities.
| File | Kind | Size |
|---|---|---|
| README.zh-CN.md | markdown | 7.9 KB |
| SKILL.md | skill md | 22.7 KB |
| agents/openai.yaml | config | 336 B |
| evals/runtime-scenarios.json | config | 4.9 KB |
| evals/scenarios.json | config | 25.9 KB |
| references/protocol.md | markdown | 35.0 KB |
| references/research-basis.md | markdown | 5.3 KB |
| references/runtime-evidence.md | markdown | 16.7 KB |
| scripts/gas_runtime.py | script | 22.9 KB |
| templates/dispute.example.json | config | 2.4 KB |
| templates/release.example.json | config | 1.6 KB |
| templates/review.example.json | config | 1.7 KB |
| templates/run.example.json | config | 6.3 KB |
| templates/runtime.example.json | config | 5.0 KB |
| templates/task.example.json | config | 6.4 KB |
templates/review.example.json
View on GitHub{
"schema_version": 2,
"example_only": true,
"task_id": "INVITE-API-001",
"reviewer_identity": null,
"author_identities": [],
"independence_verified": false,
"contract_version": "draft-1",
"base_commit": null,
"head_commit": null,
"integration_commit": null,
"verdict": "NOT_RUN",
"checks": [],
"blocking_findings": [],
"unverified_items": [
"所有检查均未执行;空的缺陷列表不代表通过。"
],
"release_authorized": false,
"notes": "接收执行者实际检查、监控原始输出并核对方法、退出码、日志、时间、精确提交与覆盖;需要时复跑已有命令,补证退具名执行者,不编写或修改测试/验证代码。每项检查分别记录 execution 与 result;独立裁衡保留本记录 verdict;风险接受、人类决定与实际交付在附表分维引用,不引入管理接受权。",
"run_id": "example-team-invitations",
"reviewer_role": "arbiter",
"reviewer_epoch": null,
"rule_references": [],
"dispute_ids": [],
"review_record_id": null,
"runtime_evidence_ref": null,
"intent_coverage_matrix": [],
"review_method_ref": null,
"received_output_refs": [],
"monitor_evidence_refs": [],
"evidence_supplement_requests": [],
"review_boundary": {
"test_code_write_allowed": false,
"analysis_only": true,
"existing_command_rerun_allowed": true,
"note": "裁衡者分析执行者输出及可用监控证据、规则忠实性与精确候选;不得编写或修改测试/验证代码。每项补证请求绑定 task_id、criterion_id、executor_name、executor_identity/epoch、缺口与所需原始证据;由该项具名执行者补齐,不以签名代替独立验收。"
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |