본문으로 건너뛰기
cccskills
무료GitHub에 공개

session-share

Use when the user asks to beam, publish, or share the current local coding session to an authenticated remote receiver. Not for viewing a transcript locally: use session-viewer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(2)

  • SKILL.md6.4 KB
  • agents/openai.yaml186 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Session share

Contract

FieldBound contract
TriggerUser explicitly asks to beam, publish, or share the current local coding session with an authenticated remote receiver.
AuthorityRemote: uploads a redacted, size-bounded JSON payload to a configured endpoint over HTTPS with authentication; requires explicit human invocation. Previews the payload size and destination before sending. No model-autonomous invocation.
Side effectA redacted, size-bounded JSON payload is uploaded to a configured endpoint over HTTPS with authentication; a shareable URL is returned. No raw JSONL, reasoning traces, or credentials are sent.
DoneThe returned URL is valid and the payload contains only visible user/assistant messages and aggregate tool counts.

Not for

  • Viewing or exporting a session transcript locally; use session-viewer.

Inputs

  • Required: the current local coding session transcript (visible user and assistant messages, tool-call metadata).
  • Required: target endpoint URL (HTTPS). The user must supply or have configured it.
  • Required: authentication credentials for the endpoint. The user must supply or have configured them; the skill never invents credentials.
  • Optional: a session-end hook configuration that may invoke sharing automatically at session end. Synchronization is opt-in and off by default.

Payload contract

The payload is a single JSON object:

{
  "messages": [
    {"role": "user", "text": "..."},
    {"role": "assistant", "text": "..."}
  ],
  "tool_counts": {"tool_name": integer, ...},
  "size_bytes": integer
}
  • messages: visible user and assistant messages only. Exclude raw JSONL, reasoning or thinking traces, tool result bodies, and any credential- or secret-bearing content.
  • tool_counts: aggregate invocations per tool name (total count), not individual tool inputs or outputs.
  • size_bytes: the serialized payload size in bytes, measured before upload.

The size limit is 5 MB (5,242,880 bytes). If the serialized payload exceeds this limit, drop the oldest non-essential messages while preserving tool_counts until the payload is at or below the limit. If the payload still exceeds 5 MB after dropping all non-essential messages, stop and report the measured size; do not upload.

HTTP contract

Upload is a single POST request:

  • Method: POST
  • URL: the configured endpoint URL (must be HTTPS)
  • Header: Authorization: Bearer <token> or the credential format the endpoint requires
  • Header: Content-Type: application/json
  • Body: the serialized payload JSON

The endpoint response is JSON. The skill reads the shareable URL from the response body. The expected response shape:

{"url": "https://...", ...}

If the response is not valid JSON, or the url field is absent or not a valid HTTPS URL, the upload failed; report the response status and body excerpt.

Procedure

  1. Confirm the user explicitly requested sharing this session. If the request is ambiguous or model-initiated, stop and ask for explicit human confirmation. Done when: explicit human intent is confirmed.
  2. Extract visible user and assistant messages from the transcript. Exclude raw JSONL, reasoning traces, tool result bodies, and credential-bearing content. Aggregate tool-call counts (total invocations per tool name). Done when: only visible messages and aggregate counts are selected.
  3. Serialize the payload JSON and measure its size. If it exceeds 5 MB, drop the oldest non-essential messages while preserving tool_counts until it is at or below 5 MB. If it still exceeds 5 MB, stop and report the measured size. Done when: the payload is within the 5 MB limit or the blocked result is reported.
  4. Preview the payload to the user: state the byte size, the message count, the destination endpoint URL, and that a redacted JSON payload will be uploaded over HTTPS. Wait for an explicit yes. Done when: the user confirms after seeing the preview, or the user declines and the run stops.
  5. Validate that authentication credentials are available for the endpoint. Done when: credentials are confirmed present, or the missing prerequisite is reported and no payload is sent.
  6. POST the payload to the endpoint over HTTPS with the authentication header and Content-Type: application/json. Done when: the upload completes with an HTTP response, or the network or HTTP error is reported.
  7. Parse the response JSON and extract the url field. Validate that it is a well-formed HTTPS URL. Done when: the URL is validated, or the response failure is reported.
  8. Optional session-end hook: if the user has configured a session-end hook command (configuration example only), it may invoke this procedure automatically at session end; synchronization remains opt-in and is off by default. Done when: the hook configuration is noted or confirmed absent.

Failure and recovery

  • Ambiguous or model-initiated request: stop, do not upload, ask for explicit human confirmation.
  • Missing credentials: stop before any upload; report that endpoint credentials are not configured; no payload is sent.
  • Human rejects preview: no upload occurs. The run stops. Report that the user declined.
  • Payload exceeds 5 MB after dropping non-essential messages: report a blocked result with the measured size; do not upload an oversized payload.
  • Upload failure (network timeout, DNS failure, TLS error): report the exact error and the blocked result; no URL is returned. Do not retry blindly.
  • HTTP error (4xx or 5xx): report the status code and a short response body excerpt; no URL is returned. Do not retry blindly.
  • Response lacks valid URL: report the response status and body excerpt; no URL is returned.
  • Redaction leak detected (reasoning, credentials, or raw JSONL present in the payload): abort before upload; report the leak; do not publish.
  • Non-mutation rule: publishing is irreversible once the URL is returned; the only protection is to never upload a payload that fails the redaction contract.

Output

On success, a valid shareable URL plus confirmation that the published payload contains only visible user/assistant messages and aggregate tool counts. On failure, a blocked result naming the failure class with no URL published.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for the DMA stream itself: use dma-baremetal.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

af-xdp

무료

Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy versus zero-copy mode. Not for full kernel bypass: use dpdk.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body, with human approval and preview. Not for automated or model-initiated insertion.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

agents-md

무료

Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential, publish, deploy, or irreversible changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

OutlineDriven의 스킬 모두 보기

이 스킬의 문제 신고