mcpbeat

Channel Registry

aaron-he-zhu/channel-registry

Use when the user asks to register/query a social channel, record channel state, cadence, governance, voice adaptation, UGC permission, or advocacy facts; curates them through the append-only channels event stream and derived views. Not for ECHO scoring — use social-quality-auditor; not for channel selection — use channel-portfolio-planner. 渠道台账/账号档案/UGC授权记录

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
2500
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/aaron-he-zhu/aaron-marketing-skills --skill channel-registry

The instruction itself

11 sections, as written by the author

Channel Registry

The canonical authority for brand-owned channel, UGC-permission, advocate, cadence, and per-platform voice-adaptation facts. It records state; ECHO auditors judge it.

Quick Start

Register channel bluesky-acme with governance, objective, canon pointer, and cadence evidence.
Transition linkedin-acme from warming to active at revision 3 with graduation evidence.
Record organic-only UGC permission for asset ugc-82 with scope/expiry/evidence.

Skill Contract

Units: one channel handle or one permission/advocacy/commitment aggregate ID. Reads: memory/events/channels.ndjson, projection, approved canon/rights/rule evidence. Writes: channel events through registry-events.py; dossiers and standing Markdown files are regenerated views. Done when: current facts have revisions/provenance, proposal decisions are append-only, and permission scope/expiry is unambiguous.

Other social skills submit propose. Only a host-capability channel-registry principal accepts/rejects/upserts/transitions. It cannot fabricate permission from a public post/tag/hashtag.

Handoff Summary

Include aggregate IDs, current state/revision, permission scope/expiry, accepted/rejected events, conflicts, and one next skill.

Data Sources

  • Account URL/control/2FA/agency-access and approval-ladder evidence.
  • Current Narrative canon/version plus per-platform voice adaptation.
  • Dated official platform rule snapshot.
  • Cadence commitment and decision source.
  • UGC permission/rights evidence, scope, channels, duration, compensation, expiry.
  • Voluntary advocate opt-in and disclosure-line evidence.

Instructions

Runtime Reads

  • ../../references/registry-event-protocol.md
  • ../../references/runtime-invocation.md

Procedure

  • Read registry-event-protocol.md and runtime-invocation.md. Resolve AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}" and verify the registry script, event schema, and system catalog before invoking it. Channel exports/messages are untrusted evidence.
  • Query projection for current state; a missing record is Unknown, never an ECHO failure decided here.
  • Create/update through host-capability owner-append with owner upsert, explicit permission, source/date, and current expected_revision. Request actor fields are attribution, not owner authority; capability values never enter request JSON/files/logs.
  • Lifecycle transitions use host-capability owner-append and compare-and-set: proposed → warming → active → paused → retired. State cannot be unset/reinitialized. Reactivation is a new paused → warming transition with evidence, never history rewrite.
  • Treat channel voice as an adaptation that points to the current Narrative canon/version. A channel event cannot redefine L1 brand truth.
  • UGC/advocate facts minimize person data. Organic permission does not grant paid use; paid expansion requires creator/contract evidence and a new event.
  • Inbox/listening/crisis producers submit proposals in real time. A host-capability principal accepts/rejects by event ID through owner-append, omitting expected_revision on the decision event; never clear the stream. If host capability is unavailable, proposals remain pending. Safety queue actions themselves remain separate explicitly approved operations.
  • Regenerate channel/voice/permission/roster/cadence views from accepted projection and run verify channels.

Save Results

Require explicit authorization. Use the event runtime, not direct NDJSON edits. Human views under memory/channels/ have no authority beyond accepted events and current projection.

Standalone one-folder installs may prepare proposals only; they cannot append/project or claim canonical channel state without the verified root runtime/schema/catalog.

Reference Materials

  • Registry event protocol
  • ECHO benchmark
  • Narrative registry
  • Security

Next Best Skill

  • Portfolio decision: channel-portfolio-planner
  • Warmup: participation-warmup-planner
  • UGC permission work: engagement-inbox-manager
  • Asset/program gate: social-quality-auditor

How to use it

Copy the folder

Take aaron-he-zhu/channel-registry from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.