What does this skill do, and when should you use it?
Social Calendar Builder creates or rebalances an always-on brand social posting calendar. It plans pillar allocation, hero/hub/help and give:ask targets, recurring channel slots, queue depth, batching, evergreen recycling, and reserved realtime gaps. Trend gaps are filled only after a trend-spotter go verdict, and no batch enters the queue without a SHIP verdict from social-quality-auditor. It does not write individual posts, repurpose existing assets, plan paid amplification, or automate publishing or scheduling.
Reads active channels and committed cadence from the channel registry, content pillars and voice-card pointers, trend-spotter go/skip verdicts, dated platform norm cards, and user-provided analytics exports; maps recurring slot types and queue depth by channel; defines batch days, cross-channel publish order, link and first-comment operations; selects measured evergreen candidates and attaches freshness re-checks; reserves realtime gaps; writes confirmed calendars to memory/social/social-calendar-builder/; and submits cadence changes as operation: propose events through registry-events.py.
- A social lead needs a four-week always-on calendar for Bluesky, LinkedIn, and Xiaohongshu.
- A team is over-posting on LinkedIn and needs queue depth rebalanced against committed cadence and hosting capacity.
- A content team wants an evergreen rotation built from its top 20 measured posts with freshness checks.
- A brand wants deliberate open slots for trends that are filled only after a trend-spotter go verdict.
- An operations team needs a pre-publish workflow where the next batch cannot enter the queue without SHIP.
How do you install this skill?
- Confirm that the channel registry, proposal path, trend verdicts, dated platform norm cards, and quality auditor are available and version-compatible before use.
- Do not treat Estimated ratios as platform rules; recalibrate them with dated first-party analytics.
- This skill plans but does not publish; queue movement requires a SHIP verdict from social-quality-auditor and user confirmation for memory writes.
- The many relative references and cross-skill dependencies may fail when this skill is installed in isolation.
- Shell / CLI
- Network access
- Local filesystem
Python standard library
To install the collection in Claude Code, run /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, then /plugin install aaron-marketing@aaron. On an Agent Skills-compatible host, run npx skills add aaron-he-zhu/aaron-marketing-skills, or clone it with git clone https://github.com/aaron-he-zhu/aaron-marketing-skills. The supplied material does not document a separate standalone installer for this skill.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/social/craft/social-calendar-builder" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Use a trigger such as: Build the always-on calendar for Bluesky, LinkedIn, and 小红书 — pillars: [list]. Use the committed cadence in the registry; horizon 4 weeks. You can also ask it to rebalance over-posting or plan an evergreen recycle rotation. Provide channels, committed cadence, content pillars, and planning horizon. Every ratio must be labeled Estimated with a named source and calibration date. After delivery, the skill asks whether to save the results.
What are this skill's strengths and limitations?
- Produces an actionable calendar covering pillars, channel slots, queue depth, batching, and evergreen recycling.
- Separates Estimated starting heuristics from measured user analytics.
- Builds in trend go/skip decisions, crisis queue pauses, and a SHIP/FIX/BLOCK publishing gate.
- Clearly prohibits automated publishing, scheduling, and automation on Chinese platforms.
- A complete result depends on registry state, project memory, trend verdicts, platform norm cards, and user analytics exports.
- It does not write individual social posts or handle repurposing and paid amplification.
- Ratios are starting heuristics and require calibration against first-party analytics.
- The supplied material does not document a dedicated test suite or platform-by-platform validation for this skill.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Evergreen Social Calendar this page | 59 · Recommended | ★ 3k | 13d ago | Apache-2.0 |
| Narrative Cascade Planner | 58 · Recommended | ★ 3k | 13d ago | Apache-2.0 |
| Channel Portfolio Planner | 57 · Use with care | ★ 3k | 13d ago | Apache-2.0 |
| Influencer Discovery | 51 · Use with care | ★ 3k | 13d ago | Apache-2.0 |
| Trend Spotter | 49 · Use with care | ★ 3k | 13d ago | Apache-2.0 |
Unlike social-creative-builder, this skill plans the calendar, pillars, and cadence rather than writing individual platform-native posts. Unlike content-amplifier, it handles organic evergreen scheduling rather than repurposing assets or planning paid amplification.
How did FollowSkills review this skill?
The skill explicitly limits itself to calendar planning, prohibits posting automation, requires confirmation before memory writes, uses an authorized propose path, and requires a SHIP audit gate. It also identifies pasted exports and scraped content as untrusted and describes read/write locations. Deductions apply because it depends on registries, auditors, and host permissions without specifying complete rollback, data minimization, or concrete protection for sensitive analytics exports.
Inputs, outputs, completion conditions, termination rules, and several abnormal states are described, including missing cadence, FIX/BLOCK, skip, and crisis pauses. Deductions apply because the key runtime, registry behavior, and cross-skill dependencies are not reproduced in this file, and no skill-specific execution tests or static error implementation are supplied; the static ceiling therefore limits this dimension to 10.
Triggers, inputs, output shape, and non-fit boundaries are clear for evergreen calendars, pillar allocation, queue depth, trend gaps, and bilingual channels. Chinese platforms are explicitly manual-package/user-export paths, so the core function does not require unreachable overseas automation. Deductions apply because boundaries and degradation paths for varying team capacities, platform policies, and missing inputs remain limited.
The document has clear progressive structure, frontmatter, Quick Starts, a contract, data sources, numbered instructions, save rules, references, next-skill handoffs, versioning, and Apache-2.0 licensing. Deductions apply because a maintainer, update path, changelog, and dependency-version policy are not explicit in the skill, while numerous relative references may create portability and maintenance risk.
The expected output is concrete and operationally usable: pillar allocation, ratios, recurring slots, queue depth, batching, evergreen recycling, trend gaps, and publish-order notes. Deductions apply because completion depends on registry state, analytics exports, norm cards, and multiple companion skills; this review is static and contains no representative output or execution evidence, so the score stays within the static ceiling of 7.
The skill requires sources and calibration dates for ratios and distinguishes Estimated, Measured, and user-provided data; it also points to framework, norm-card, and audit-gate references. Deductions apply because it contains no actual calibration results, independent reproduction record, or dedicated tests covering its key paths; static evidence is therefore limited to 5.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →