aaron-he-zhu/aaron-marketing-skills / social/craft/social-calendar-builder
social-calendar-builder
VerifiedUse when the user asks to "build our social posting calendar", "set weekly slots and queue depth per channel", or "plan the evergreen recycle rotation"; produces the always-on brand calendar — pillar allocation with hero/hub/help balance and give:ask targets (all labeled Estimated starting heuristics to calibrate against own analytics, never scored rules), per-channel recurring slots with queue depth, a batching workflow, an evergreen recycle cycle with freshness re-checks, deliberate open slots for realtime/trend moments fed by trend-spotter go/skip verdicts, and first-comment/publish-order ops — cadence commitments filed to the channel registry, and no batch ships to the queue without a SHIP verdict from social-quality-auditor pre-publish mode. Not for repurposing an existing asset or the paid-amplification calendar — use content-amplifier. 社媒排期/内容日历/栏目配比/常青循环复用
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.9 KB |
| references/human-action-control.md | markdown | 2.3 KB |
references/human-action-control.md
View on GitHub# Social Human Action and Rights Control
Use this control when a social package moves from drafting or gating to human posting, replying, moderating, pausing, unpausing, or removal. It does not add posting automation to any platform.
## Package and gate binding
Bind a package or batch with `package_ref`, `package_version`, `package_hash`, target channel/account reference, and claims/norm-card offsets. A pre-publish SHIP verdict applies only to that exact hash. Editing copy, media, disclosure, destination, or channel after the gate creates a new version and requires re-gating.
## Human action receipt
The human operator records one receipt per action: `action_ref`, action type (`post | reply | moderate | pause | unpause | remove`), channel/account reference, package/version/hash when applicable, actor reference, attempted/completed time, status (`succeeded | partial | failed | unknown`), an opaque post/operation ref, and a bound evidence record. The domain evidence may preserve a live URL, screenshot, or export; the shared locator-free envelope carries only its ref and digest. Label a manually supplied receipt `User-provided`; do not upgrade it to Measured.
A plan, queue row, draft, SHIP verdict, proposal marker, or requested action is not a receipt. Without a matching receipt, state remains `planned`, `queued`, or `open`—never `published`, `replied`, `paused`, `removed`, or `done`. Human posting remains the only publication path for closed and Chinese platforms; this control authorizes no automation anywhere.
## UGC rights
Track each asset with an opaque holder/subject reference, content reference, permitted use (`organic | paid`), exact channels and placements, start/expiry, territory if relevant, compensation, evidence reference, last-verified time, and status (`active | expired | revoked | disputed | unknown`). Only `active` rights covering the exact use allow publication. Public posting, tagging, a branded hashtag, or past organic permission never implies paid rights.
Re-check rights immediately before each use. Expired, revoked, disputed, unknown, or scope-mismatched rights fail closed. Removal requests create one removal action per live placement; the queue stays open until every placement has a matching removal receipt. A registry proposal records the fact for review but is not proof that removal occurred.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |