skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
yonatangross/orchestkit78 installs

release-sync

After a version tag, syncs CHANGELOG and release notes to NotebookLM and the knowledge base, optionally a podcast. Use after tagging a release.

How do I install this agent skill?

npx skills add https://github.com/yonatangross/orchestkit --skill release-sync
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill automates the synchronization of release notes and architectural documentation from a local repository to external knowledge management systems like NotebookLM and HQ KB. While the skill correctly uses interactive prompts to obtain user consent for configuration and sync targets, it processes content from repository files (CHANGELOG, README) without sanitization. This creates an indirect prompt injection surface where a compromised or malicious repository file could influence agent behavior during the sync process.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

Release Content Sync

Sync the latest OrchestKit release to external knowledge systems.

CC ≥ 2.1.118 (M122): Sync triggers on the new claude plugin tag annotated tag (in addition to plain git tag). The tag's annotation embeds the plugin manifest version, which release-sync uses as the canonical source-of-truth for the version being synced. See src/skills/chain-patterns/references/plugin-tag.md.

What This Does

  1. Reads the latest CHANGELOG entry, CLAUDE.md, and hook README
  2. Updates the OrchestKit NotebookLM KB notebook with fresh sources
  3. Ingests the release digest into HQ Knowledge Base (if available)
  4. Optionally generates a new podcast from the updated notebook

Prerequisites

  • MCP servers: notebooklm-mcp and/or hq-content
  • NotebookLM notebook ID stored in .claude/release-sync-config.json

Step 1: Detect Version and Read Sources

# Read current version from CLAUDE.md
version = Grep(pattern="Current.*\\d+\\.\\d+\\.\\d+", path="CLAUDE.md")

# Read CHANGELOG — extract latest release section
changelog = Read("CHANGELOG.md", limit=80)

# Read hook architecture summary
hook_readme = Read("src/hooks/README.md", limit=100)

# Read CLAUDE.md for project overview
claude_md = Read("CLAUDE.md")

Step 2: Load Config

config = Read(".claude/release-sync-config.json")
# Expected format:
# {
#   "notebooklm_notebook_id": "0a05e680-e33b-4d8c-94b2-5df26a1af329",
#   "hq_kb_project": "orchestkit"
# }

If config doesn't exist, prompt user:

AskUserQuestion(questions=[{
  "question": "NotebookLM notebook ID for OrchestKit KB?",
  "header": "Configuration",
  "options": [
    {"label": "Use default", "description": "OrchestKit v7 — Complete KB (0a05e680...)"},
    {"label": "I'll provide", "description": "Enter a custom notebook ID"}
  ]
}])

Step 2b: Choose Sync Targets

Ask for the four target values: notebooklm, hq_kb, slack, notes.

# Skip the form when targets are explicit:
#   release-sync --targets=notebooklm,slack  → skip, use those
#
# Otherwise ask. This used to prefer an ork-elicit MCP form and fall back to
# AskUserQuestion; the server was retired (EPIC C mechanism 11) because
# AskUserQuestion is the CC-native surface for this and a permanent MCP tool
# slot to restate it was the parallel mechanism. One path now.
#
# ALL targets default to False — OrchestKit is open-source and these targets
# (notebook IDs, HQ KB, Slack) are user-private infrastructure the plugin
# cannot assume is configured. The user explicitly opts in.
targets = {
  "notebooklm": ask_yn("Push to NotebookLM?", default=False),
  "hq_kb":      ask_yn("Push to HQ KB?",       default=False),
  "slack":      ask_yn("Announce in Slack?",   default=False),
  "notes":      ""
}

Three AskUserQuestion round-trips. The rest of this skill reads targets["notebooklm"], targets["hq_kb"], targets["slack"], targets["notes"] regardless of source.

Privacy note: all targets are opt-in (default false). NotebookLM notebook IDs and HQ knowledge bases are user-private — the open-source plugin must not assume they exist or push to them implicitly.

Step 3: Update NotebookLM Sources

# Probe MCP availability
ToolSearch(query="select:mcp__notebooklm-mcp__source_add")

# Add release digest as new source
mcp__notebooklm-mcp__source_add(
  notebook_id=config.notebooklm_notebook_id,
  source_type="text",
  title=f"Release {version} — {date}",
  text=release_digest,
  wait=True
)

Step 4: Ingest to HQ Knowledge Base (Optional)

# Probe HQ content MCP
ToolSearch(query="select:mcp__hq-content__knowledge_ingest")

# If available, ingest
mcp__hq-content__knowledge_ingest(
  title=f"OrchestKit {version} Release Notes",
  content=release_digest,
  project="orchestkit",
  content_type="release-notes"
)

Step 5: Generate Podcast (Optional)

AskUserQuestion(questions=[{
  "question": "Generate a podcast from the updated notebook?",
  "header": "Podcast",
  "options": [
    {"label": "Yes — deep dive", "description": "~10 min podcast covering all changes"},
    {"label": "Yes — brief", "description": "~3 min summary"},
    {"label": "No", "description": "Skip podcast generation"}
  ]
}])

if podcast_requested:
  mcp__notebooklm-mcp__studio_create(
    notebook_id=config.notebooklm_notebook_id,
    artifact_type="audio",
    audio_format=selected_format,
    confirm=True
  )

Output

Report what was synced:

Release Sync Complete — v{version}
  NotebookLM: source added to {notebook_title}
  HQ KB: ingested as release-notes/{version}
  Podcast: generating (poll with studio_status)

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/yonatangross/orchestkit/release-sync">View release-sync on skillZs</a>