agent-transcript
Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
Share a redacted coding session or hand its logical conversation to an authenticated OpenClaw Gateway.
Claude Code
$ npx -y skills add openclaw/agent-skills --skill beam --agent claude-code
Codex
$ npx skills add openclaw/agent-skills --skill beam -a codex -y
Cursor
$ npx skills add openclaw/agent-skills --skill beam -a cursor -y
Gemini CLI
$ npx skills add openclaw/agent-skills --skill beam -a gemini-cli -y
GitHub Copilot
$ npx skills add openclaw/agent-skills --skill beam -a github-copilot -y
OpenCode
$ npx skills add openclaw/agent-skills --skill beam -a opencode -y
Windsurf
$ npx skills add openclaw/agent-skills --skill beam -a windsurf -y
name: beam description: "Share a redacted coding session or hand its logical conversation to an authenticated OpenClaw Gateway."
Use when the user explicitly asks to beam, publish, or share the current local coding session with an authenticated OpenClaw receiver.
Set or obtain the destination receiver URL first:
export BEAM_ENDPOINT="https://gateway.example.com/api/v1/beam/sessions"
Prefer the harness-specific exact identifier. Resolve the directory containing this `SKILL.md` as `BEAM_SKILL_DIR` first.
Claude Code exposes the current session id:
node "$BEAM_SKILL_DIR/scripts/beam" publish \
--endpoint "$BEAM_ENDPOINT" \
--session-id "${CLAUDE_SESSION_ID}"In Codex, resolve the directory containing this `SKILL.md` as `BEAM_SKILL_DIR`; normal shell-tool children expose the current thread id:
node "$BEAM_SKILL_DIR/scripts/beam" publish \ --endpoint "$BEAM_ENDPOINT" \ --thread-id "$CODEX_THREAD_ID"
Prefer exact harness metadata when available:
Useful options:
node "$BEAM_SKILL_DIR/scripts/beam" publish --endpoint "$BEAM_ENDPOINT" --session /path/to/session.jsonl node "$BEAM_SKILL_DIR/scripts/beam" publish --endpoint "$BEAM_ENDPOINT" --thread-id "$CODEX_THREAD_ID" node "$BEAM_SKILL_DIR/scripts/beam" publish --endpoint "$BEAM_ENDPOINT" --title "Fix upload flow" node "$BEAM_SKILL_DIR/scripts/beam" publish --endpoint "$BEAM_ENDPOINT" --complete node "$BEAM_SKILL_DIR/scripts/beam" publish --endpoint "$BEAM_ENDPOINT" --dry-run
`--dry-run` prints the sanitized payload locally and performs no network request.
On success, return only the Beam URL and a short disclosure summary: source harness, shared message count, whether older entries were truncated, and whether the beam is complete. The URL uses the endpoint-derived Control UI base path followed by `/beam/<title-slug>-<id-prefix>`, for example `https://gateway.example.com/beam/fix-upload-flow-0123456789ab`. The title comes from `--title` or the first shared user message. The stable ID suffix identifies the session; links with an earlier title remain valid.
If the receipt includes `canView: false`, say that the upload succeeded and the link is for authorized Team operators; upload-only access does not let the guest open it. Do not present it as a guest-viewable link. Staff and older receipts may omit `canView`; omission is not a new access grant.
Guest access requires receiver-side support and operator authorization. Sender support alone does not mean it is deployed. Current Visitor-enabled receivers let active verified publishers create, refresh, list, and read only their own snapshots. They grant no shared-catalog access or deletion. Updated receivers allow authorized continuation of a publisher's own explicitly released Beam, subject to normal destination creation, model, account and session permissions. Older upload-only receivers can return `canView: false`; honor that receipt. Guests need no shared secret. If personal access expires, sign in again outside hooks or refresh the personal `BEAM_ACCESS_TOKEN`. Revoked access needs an authorized operator to restore it. Never blindly retry an uncertain upload.
Only perform this when the user asks to move or continue the conversation in Team; permission to share a snapshot alone is insufficient. Requires Node 22.13+ and an updated receiver.
node "$BEAM_SKILL_DIR/scripts/beam" handoff --endpoint "$BEAM_ENDPOINT" --thread-id "$CODEX_THREAD_ID" node "$BEAM_SKILL_DIR/scripts/beam" read --endpoint "$BEAM_ENDPOINT" --beam-id BEAM_ID --profile-dir /path/to/own/remote-profile node "$BEAM_SKILL_DIR/scripts/beam" continue --endpoint "$BEAM_ENDPOINT" --beam-id BEAM_ID --profile-dir /path/to/own/remote-profile --message "Continue the work"
Use `--session-id` for Claude Code. The handoff receipt prints `BEAM_ID`. `--profile-dir` selects an existing normal OpenClaw remote profile for that exact Gateway; configure your own authentication first. No shared account or provider token is requested or
Shared skills for coding agents that work on OpenClaw projects. This repo is the public canonical source for common workflows such as review closeout and remote validation.
Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.
Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.
Crabbox/Testbox remote proof: portable provider routing, untrusted isolation, Linux/macOS/Windows/WSL2, live E2E, diagnostics,…
Clipboard-ready handoff prompt for another agent to investigate or continue a task.
House README standard: structure, badge row, tone, per-archetype templates, and verification gates for steipete/openclaw repos.
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.