40-next-content-plan-global
Skill644 starsChanged 6 months agoMITView on GitHub
Use when the next period content plan must be built from last period DATA — keep and replicate winners, cut losers, at most two new hypotheses, a 70/20/10 mix, a four-week overview, and an owner per slot. Trigger on 'next content plan', 'content plan for next month', 'plan from the audit', 'what should we post next quarter', 'scale what worked', 'plan content using the numbers'. Also use when a report just landed and the user asks what to do with it. Not for — auditing the past period first, see `39-content-audit-global`; turning the plan into a dated calendar, see `01-content-calendar-global`; the next period ADS plan, see `57-next-ads-plan-global`.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- minhnv0807/fullstack-mkt-skillsword for word, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- minhnv0807/fullstack-mkt-skills★ 644100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository134 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- 00-marketing-plan-globalSkill
- 01-content-calendar-globalSkill
- 02-campaign-brief-globalSkill
- 03-performance-eval-globalSkill
- 04-script-video-globalSkill
- 05-ad-copy-globalSkill
- 06-ugc-egc-brief-globalSkill
- 07-marketing-report-globalSkill
- 08-competitor-research-globalSkill
- 09-customer-insight-globalSkill
- 10-reverse-kpi-globalSkill
- 11-channel-setup-globalSkill
- 12-landing-page-brief-globalSkill
- 13-data-analysis-globalSkill
- 14-email-marketing-globalSkill
- 15-social-listening-globalSkill
- 16-marketing-psychology-globalSkill
- 17-pricing-strategy-globalSkill
- 18-referral-program-globalSkill
- 19-ab-test-setup-globalSkill
- 20-client-intake-brief-globalSkill
- 21-ads-audit-globalSkill
- 30-design-master-globalSkill
- 31-offer-design-globalSkill
- 32-seo-growth-globalSkill
- 33-b2b-lead-gen-globalSkill
- 34-ai-marketing-os-globalSkill
- 35-brand-voice-globalSkill
- 36-content-brief-globalSkill
- 37-social-caption-globalSkill
- 38-community-seeding-globalSkill
- 39-content-audit-globalSkill
- 41-campaign-asset-list-globalSkill
- 42-image-brief-globalSkill
- 43-carousel-brief-globalSkill
- 44-video-editor-brief-globalSkill
- 45-design-tool-brief-globalSkill
- 46-brand-guideline-globalSkill
- 47-design-review-globalSkill
- 48-quick-visual-brief-globalSkill
- 49-html-email-template-globalSkill
- 50-asset-resize-globalSkill
- 51-audience-research-globalSkill
- 52-account-structure-globalSkill
- 53-tracking-setup-globalSkill
- 54-media-plan-globalSkill
- 55-scaling-ads-globalSkill
- 56-retargeting-plan-globalSkill
- 57-next-ads-plan-globalSkill
- 58-positioning-globalSkill
- 59-go-to-market-globalSkill
- 60-launch-playbook-globalSkill
- 61-budget-planning-globalSkill
- 62-marketing-review-globalSkill
- 63-campaign-retrospective-globalSkill
- 64-team-brief-globalSkill
- 65-team-performance-review-globalSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Before writing a single line of plan, you need:
- Very specific: line 41
If the user cannot supply at least an audit or a post list with metrics, stop and recommend running 39-content-audit-global first.
- Distinctive: line 45
Data first, plan second: Every change in the plan must trace back to a specific line of prior-period data.
- Very specific: line 104
Write each one so it can be falsified: "If we [change X], then [metric Y] will [rise or fall by Z percent]." For test design and sample …
- Distinctive: line 184
Every change in the plan traces back to a specific line of data.
- Distinctive: line 187
No more than 2 new hypotheses, each falsifiable and each with a decision rule.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Next Content Plan (Global)
A plan without last period's data is a guess. The order is fixed: read the data, replicate the winners, test a small number of new hypotheses, then schedule. Do not change everything at once — a team that rebuilds from scratch every period never learns what works.
Information gathering — always read the old data first
Before writing a single line of plan, you need:
- The prior period's content audit (from
39-content-audit-global). If it does not exist, run that skill first. Do not plan around it. - The prior period's report (from
07-marketing-report-global) if available. - KPI targets for the new period — what changes versus last period.
- Known variables in the new period: upcoming campaign, launch, event, seasonality; changes in budget, headcount, or capacity.
If the user cannot supply at least an audit or a post list with metrics, stop and recommend running 39-content-audit-global first.
Principles
- Data first, plan second. Every change in the plan must trace back to a specific line of prior-period data.
- Replicate winners before chasing new ideas. A winner has already proved itself. Reproduce it with small variations before betting on an untested concept.
- The 70/20/10 split:
- 70 percent of output is proven format plus proven angle — the winner's formula, held constant.
- 20 percent is optimization of a winner — change the hook, the channel, or the length while keeping what worked.
- 10 percent is genuinely new — the test hypotheses.
- Maximum 2 new hypotheses per period. More than that and no single test accumulates enough data to conclude anything.
- Losers are not automatically deleted. Separate a loser caused by a wrong angle (retire it) from a loser caused by weak execution (fix the execution, try once more).
- Plan at the week level here. Day-level detail belongs to
01-content-calendar-global. - Account for seasonality in paid amplification. Q4 media costs run well above Q1 globally; if a proven post type is normally boosted, the same plan costs more in November than in January (see
references/benchmarks-global.md).
Workflow
1. Review the prior period
From the audit (39-content-audit-global) and report (07-marketing-report-global), fill three columns:
| Worked (KEEP) | Did not work (STOP) | Not yet tried (TEST) |
| [format / angle / channel + the numbers that prove it] | [+ the data reason] | [idea from a pattern or a new insight] |
2. Set the direction for the new period
| Period | Primary objective | Priority KPI | Attached campaign | Major change |
Exactly one primary objective — reach, lead generation, conversion, or retention. The priority KPI is the metric this period will actually be judged on.
3. Build the content mix at 70/20/10
| Group | Share | Content |
| Proven (70%) | ~70% of posts | Winner formula held constant — only the subject changes |
| Optimized (20%) | ~20% of posts | Variations on winners: different hook, channel, or length |
| Experimental (10%) | ~10% of posts | New hypotheses (maximum 2) |
Then adjust the funnel and format ratios, with a data reason for each change:
| Dimension | Prior period ratio | New period ratio | Reason (from data) |
| TOFU / MOFU / BOFU | |||
| Video vs static vs text | |||
| Channel split |
4. Plan the winner replication
| Original winner | Result (metric) | Replicate into | What changes | Channel / timing |
Each winner becomes 2-3 variations. Hold the hook structure and format constant; change the subject, the angle of the shot, or the person on camera.
5. Define the new hypotheses (maximum 2)
| Hypothesis | Format | Channel | Metric | Test duration | Decision rule |
Write each one so it can be falsified: "If we [change X], then [metric Y] will [rise or fall by Z percent]." For test design and sample sizing, hand off to 19-ab-test-setup-global.
6. Build the overview calendar and assign ownership
| Week | Theme | Priority channel | Posts | Highlights (replicated winner / hypothesis) |
| Week 1 | ||||
| Week 2 | ||||
| Week 3 | ||||
| Week 4 |
| Owner | Responsibility | Posts per week | Primary channel |
Day-level detail (publish time, hook, CTA, status) goes to 01-content-calendar-global. Per-piece briefs go to 36-content-brief-global.
Output structure
File name: next-content-plan-[brand]-[YYYYMMDD].md
# Next Content Plan — [Period] — [Brand]
## I. Prior period review
| Worked (keep) | Did not work (stop) | Not yet tried (test) |
|---------------|---------------------|----------------------|
| | | |
## II. Direction for the new period
| Period | Primary objective | Priority KPI | Attached campaign | Major change |
|--------|-------------------|--------------|-------------------|--------------|
| | | | | |
## III. Content mix — 70/20/10
| Group | Share | Posts | Content |
|-------|-------|-------|---------|
| Proven (70%) | | | |
| Optimized (20%) | | | |
| Experimental (10%) | | | |
| Dimension | Prior ratio | New ratio | Reason (from data) |
|-----------|-------------|-----------|--------------------|
| TOFU / MOFU / BOFU | | | |
| Video vs static vs text | | | |
| Channel split | | | |
## IV. Winner replication
| Original winner | Result | Replicate into | What changes | Channel / timing |
|-----------------|--------|----------------|--------------|------------------|
| | | | | |
## V. New hypotheses (max 2)
| Hypothesis | Format | Channel | Metric | Test duration | Decision rule |
|------------|--------|---------|--------|---------------|---------------|
| | | | | | |
## VI. Overview calendar
| Week | Theme | Priority channel | Posts | Highlights |
|------|-------|------------------|-------|------------|
| | | | | |
## VII. Ownership
| Owner | Responsibility | Posts per week | Primary channel |
|-------|----------------|----------------|-----------------|
| | | | |Related skills
39-content-audit-global: required input — run it first. No audit means no plan.07-marketing-report-global: the prior period's report adds the full-funnel KPI view.01-content-calendar-global: takes this plan and produces the day-by-day schedule.36-content-brief-global: briefs each individual piece inside the plan.19-ab-test-setup-global: designs the tests for the 2 hypotheses.13-data-analysis-global: supporting analysis when the data needs a deeper look.
Quality checklist
- Prior period data present as the basis (audit from 39 or report from 07) — nothing planned on instinct.
- Every change in the plan traces back to a specific line of data.
- Content mix follows 70/20/10 and the shares total 100 percent.
- Each winner has a concrete replication plan (2-3 variations each).
- No more than 2 new hypotheses, each falsifiable and each with a decision rule.
- Losers separated into wrong angle (retire) versus weak execution (fix and retry once).
- Funnel and format ratio changes each carry a data reason — nothing changed arbitrarily.
- Overview calendar covers all 4 weeks with named owners.
- Seasonality accounted for where the plan depends on paid amplification.
- Handoffs stated:
01-content-calendar-globalfor the detailed schedule,19-ab-test-setup-globalfor the hypotheses.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

