Agent skill · writing content · jeremylongshore
blog-editorial-calendar
Operate an evidence-backed editorial queue, balance topic and format coverage, schedule approved drafts, and reconcile backlog state with the publishing system. Use when choosing or scheduling the next blog work. Trigger with "show the editorial calendar" or "pick the next topic".
Why this skill is useful
Adds an automated scheduling and topic selection system that integrates with existing content workflows, providing capabilities not typically available in standard blogging tools.
What it needs
About 4k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Editorial Calendar Operations Overview Maintain a durable editorial backlog and select the next work from evidence rather than intuition. This skill balances configured topic clusters and post formats, reserves publishing slots, and reconciles local state with the real CMS before changing the queue. It coordinates blog-topic-research and seo-blog-writer; it does not replace their research, drafting, review, or publishing controls. Prerequisites An approved config.json defining targetplatform, author, UTC cadence, cluster targets, format targets, and CMS tag mappings A writable backlog.json with stable IDs, titles, clusters, formats, evidence URLs, priorities, statuses, and scheduled timestamps Read-only CMS listing access for sync; separate approved write access only when the user requests scheduling or publication blog-topic-research for backlog replenishment and seo-blog-writer for draft production Topic and format target weights that each total approximately 1.0 Tool Discipline Use Read to inspect configuration and backlog state. Use WebSearch and WebFetch only to confirm public evidence or read the authorized CMS inventory. Use Write or Edit for reviewed, secretless state updates; never write credentials, raw access tokens, or unpublished sensitive content into receipts. Instructions 1. Parse the requested action: status, next, add, mark-done, or sync. Reject unknown actions and mutually incompatible scheduling flags. 2. Read and validate config.json and backlog.json. Confirm unique IDs, valid statuses, parseable UTC timestamps, nonnegative priorities, and target weights near 1.0. 3. Run a read-only reconciliation before selection. Match CMS records by stable CMS ID first, canonical URL second, and normalized slug only as a last resort. Report ambiguous matches instead of guessing. 4. For next, score only eligible ready items. Rank cluster deficit first, then format deficit, evidence strength, explicit priority, and oldest creation time. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/blog-editorial-calendar