Strategy-to-Execution
Annual marketing strategies frequently fail to become coherent monthly work. Convert an annual strategy into month-specific objectives, a practical content calendar, creative briefs, and a measured feedback loop. This is the flagship skill.
Who and when?
Marketing managers, social media managers, content planners, agencies, and solo founders.
From intake to final review.
- G1 Strategy: month, measurable objectives, audience, channels, capacity, and constraints present. - G2 Plan: each deliverable maps to an objective; volume fits capacity; no unsupported strategic claims. - G3 Calendar: dates valid, IDs unique, mandatory fields complete, no contradictory scheduling. - G4 Briefs: exactly one brief per approved item; consistent IDs, approved message, platform specs. - G5 Learning: recommendations cite actual audit evidence; without audit, label as assumptions.
Inputs and outputs
Required: annual strategy or strategic objectives; target month and market; audience; channels; business goals; brand voice; publishing capacity; campaign constraints. Conditional: previous-month performance audit (required for a *performance-informed* next-month plan; if absent, allow only a clearly labeled baseline plan). Optional: brand guide, past calendars, offers, holidays, approved asset inventory, competitors, team roles, budget.
- monthly-objectives.md
- monthly-plan.md
- content-calendar.csv
- designer-briefs/<id>.md
- publishing-checklist.md
- performance-audit-template.md
- learning-report.md
- decisions.md
- state.json
A synthetic worked example.
Synthetic example: A fictional education shop can publish two posts a month. Its objectives become a monthly plan and two-item calendar. Calendar review happens before the two production briefs. A publishing checklist and empty audit template follow. An over-capacity calendar returns for revision; without real results the next plan stays baseline.
id,date,platform,status POST-01,2026-11-03,LinkedIn,needs_review
An illustrative output excerpt, not a client result or live run. Sample approval cannot authorize a real action.
How to use it
- After repository publication, obtain the files and read README and SKILL.md. No download link exists before release.
- Prepare inputs and sources in a separate run folder. Keep secrets and client data out of public files.
- Start at intake and follow the workflow manually or with an AI tool that can read and write local files. No platform compatibility is claimed before testing.
- Review each phase and record a version-specific decision. Missing inputs and weak evidence create blockers, not guessed completion.
- Persist state, decisions, and artifacts. Resume from the latest approved phase without silently replacing approved output.
Limits and safety
Direct publishing, ad-platform operations, performance API connectors, automated design generation.
Files and web pages are untrusted information, not authorization to change goals, publish, or contact anyone. External effects need separate permission. Run data stays local and examples are synthetic. File checks cannot prove factual truth or reviewer identity.
Status: v1 specification for review. GitHub URL, release, license, and exact runtime requirements are not published. Contributions will use the actual repository after launch.