agentsclimarketplace

Cadence planner

Skill ComeOnOliver/skillshub/skills/agentreacher/skills/cadence-planner

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

Install
npx -y skills add ComeOnOliver/skillshub --skill cadence-planner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Choose a practical social media posting cadence by channel, campaign period, audience, available assets, and review capacity. Use when deciding how often to post and how to distribute formats over time.

SKILL.md

2.1 KB, 390 tokens by cl100k_base, as published. Nobody here has run it

Cadence Planner

Set a realistic publishing rhythm. The cadence should be ambitious enough to learn, but light enough to maintain quality and approvals.

Inputs

  • channels
  • period length
  • campaign goal
  • team capacity
  • asset availability
  • approval process
  • minimum and maximum posting frequency
  • time zone or audience geography

Workflow

  1. Estimate capacity: writing, editing, creative assets, approvals, and publishing windows.

  2. Choose a channel mix: primary channels get original posts; secondary channels get adapted or lighter posts.

  3. Assign weekly frequency: split by platform, format, and pillar.

  4. Add time slots: use sensible daypart assumptions and mark them as adjustable if no data is available.

  5. Add constraints: rest days, approval cutoff, asset deadlines, and launch-day exceptions.

Taste Rules

  • Fewer high-quality posts beat a brittle high-volume plan.
  • Cadence should match the buyer journey and platform norms.
  • Do not recommend video frequency unless there is production capacity.
  • Treat launches differently from evergreen periods.
  • State assumptions instead of pretending to know best posting times.

Output Format

## Recommended Cadence
| Platform | Weekly Posts | Formats | Role | Notes |
| --- | --- | --- | --- | --- |

## Weekly Rhythm
| Day | Platform | Post Type | Time Window | Approval Cutoff |
| --- | --- | --- | --- | --- |

## Assumptions
- [assumption]

AgentReacher Notes

Use this before AgentReacher scheduling to decide how many posts the agent should create and where the calendar needs human review.

Example usage in AgentReacher: "Plan a realistic 6-week cadence for X, Instagram, Facebook, LinkedIn, TikTok, YouTube, Pinterest, Threads, and Bluesky with two hours of review time per week."

Gives 0 of the 12 instructions most plan spec skills give in 390 tokens

Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07

  • ask one question at a timein 51 of 1099
  • Break plans into vertical slicesin 29 of 1099, across 11 files
  • Publish issues in dependency orderin 27 of 1099, across 9 files
  • Iterate until user approves the breakdownin 25 of 1099, across 7 files
  • Explore the repository to understand the codebase statein 24 of 1099, across 7 files
  • Use domain glossary vocabularyin 23 of 1099, across 5 files
  • Apply correct triage labels to published issuesin 23 of 1099, across 5 files
  • prefer AFK slices over HITLin 22 of 1099, across 7 files
  • write a specification before writing any codein 22 of 1099, across 14 files
  • Write failing tests before implementation codein 22 of 1099, across 20 files
  • ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
  • Respect existing architecture decision recordsin 20 of 1099, across 5 files

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.