跳到正文
cccskills
免费在 GitHub 公开

cg-work-memory

Use when a local agent needs to submit a concise public work-memory report for its own completed local task through `cg report work-memory`.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(3)

  • SKILL.md5.1 KB
  • examples/local-turn-summary.manifest.json1.4 KB
  • README.md2.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

CG Work Memory Skill

Use this skill with the base cg skill. The base cg skill defines the CLI safety contract; this skill defines the work-memory reporting workflow and manifest content policy.

If the base cg skill is unavailable, stop and fix the local skill setup. Do not replace it with direct CommonGround HTTP calls or raw cg worker lifecycle commands.

This skill assumes the target project has already been prepared by an operator. For local open-source demos, use the default project cg-demo unless the user explicitly provides another seeded project/profile. If the CLI returns project_not_seeded, project_bootstrap_conflict, admin_service_credential_required, or profile_auth_required, stop and report the setup error instead of running cg setup, reading PG_DSN, or calling Admin Service / CommonGround HTTP directly.

If the CLI config/profile is missing, ask the user/operator for the non-secret client connection facts instead of reading config or token files yourself: project id, agent id/profile, CommonGround service URL, Admin Service URL, and either an already prepared Admin Service bearer token file path or confirmation that CLI config has been written. Never ask for a bearer token value in chat.

Purpose

Submit selected public work facts from a local agent run as a CommonGround work-memory report.

Use this skill when:

  • A local task has completed and produced a useful public summary.
  • The task produced validation evidence, artifact references, or failure notes worth future inspection.
  • Another same-project agent, operator, or reviewer may need to audit or reference the work later.

Do not use this skill for:

  • Token-level reasoning or chain-of-thought capture.
  • Private scratchpad, local runtime state, or native memory import.
  • Credential, claim token, registration authority, grant, or admission material.
  • Managed continuation or worker lifecycle ownership.

Allowed Command

Only use these base cg skill commands:

cg profile ensure-agent --profile <project-id>/<agent-id> --project-id <project-id> --requested-agent-id <agent-id> --profile-kind byoa.work_memory_reporter.v1 --runtime-kind <runtime-kind> --display-name <display-name>
cg report work-memory --profile <project-id>/<agent-id> --project-id <project-id> --agent-id <agent-id> --manifest-file <manifest.json>

Do not call raw cg worker lifecycle commands or CommonGround HTTP APIs directly. Do not call cg setup ..., cg kernel ..., direct database commands, or any raw token/bootstrap helper from this prompt-level workflow.

Manifest Rules

Write the manifest to a JSON file before calling cg report work-memory.

The manifest must use:

  • kind: agent_work_memory_report_manifest.v1
  • request_id
  • summary
  • records
  • optional final_payload

The manifest must not include:

  • top-level meta
  • claim, claim_token, or claim handles
  • credential or registration tokens
  • grants, admission authority, or birth authority material
  • raw private traces or chain-of-thought

Recommended record roles:

  • local_turn_summary
  • execution_summary
  • validation_evidence
  • artifact_ref
  • failure_record

Recommended payload profile:

{
  "kind": "cg.turn_record.v1",
  "schema_version": "1",
  "type": "execution_summary",
  "summary": "Completed the local task and captured the reusable result.",
  "details": {},
  "refs": [],
  "producer": {
    "runtime": "local-agent",
    "component": "cg-work-memory"
  }
}

Payload fields are public work facts for inspect, audit, reference, and shared observation. They do not create authorization, contract, policy, routing, native-memory, or other machine-authoritative effects.

Workflow

  1. Summarize the completed local work in public, non-sensitive language.
  2. Create a manifest JSON file with at least one record.
  3. Ensure the local reporting profile with cg profile ensure-agent when the profile is not already prepared.
  4. Run cg report work-memory with the prepared profile.
  5. Parse only the JSON envelope from stdout.
  6. If ok is true, keep the returned turn and record_refs for future reference.
  7. If ok is false, inspect error.code and error.message; do not parse stderr as protocol data.
  8. For missing client config/profile/auth, ask for the missing client connection facts; do not ask for token contents and do not repair operator setup.

Example:

cg profile ensure-agent \
  --profile cg-demo/local-agent \
  --project-id cg-demo \
  --requested-agent-id local-agent \
  --profile-kind byoa.work_memory_reporter.v1 \
  --runtime-kind codex.local.v1 \
  --display-name "Local Agent"

cg report work-memory \
  --profile cg-demo/local-agent \
  --project-id cg-demo \
  --agent-id local-agent \
  --manifest-file examples/skills/cg-work-memory/examples/local-turn-summary.manifest.json

Read the submitted report:

cg turn context \
  --profile cg-demo/local-agent \
  --project-id cg-demo \
  --turn-id T-123

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

cg

免费

Use when a local agent needs to dispatch work to CommonGround, inspect turn or agent state, wait for a turn to close, or resume a suspended turn through the `cg` CLI instead of calling the CG HTTP API directly.

中文简介正在准备中。当前显示原文说明。

Intelligent-Internet/CommonGround1532026年5月20日 更新

cg-worker

免费

Use when deterministic runtime code needs to execute CommonGround worker lifecycle steps through the local `cg worker` command namespace, including claim acquisition, renewal, progress append, terminal finish, child dispatch, and suspend flows.

中文简介正在准备中。当前显示原文说明。

Intelligent-Internet/CommonGround1532026年5月20日 更新

查看 Intelligent-Internet 的全部技能

报告此技能的问题