Blog Editorial Calendar

What it does

When your agent uses it

• Scheduling the next blog work
• With show the editorial calendar
• Pick the next topic

Example prompts

• “show the editorial calendar”
• “pick the next topic”
• “/blog-editorial-calendar”

Requirements

• Compatibility (from SKILL.md): Designed for Claude Code; scheduling, publication, CMS reconciliation, and backlog mutation require the content owner's approval and current platform access
• Pre-approved tools (allowed-tools): Read, WebSearch, WebFetch, Write, Edit

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

1. 1Parse the requested action: status, next, add, mark-done, or sync. Reject unknown actions and mutually incompatible scheduling flags.
2. 2Read and validate config.json and backlog.json. Confirm unique IDs, valid statuses, parseable UTC timestamps, nonnegative priorities, and…
3. 3Run a read-only reconciliation before selection. Match CMS records by stable CMS ID first, canonical URL second, and normalized slug only…
4. 4For next, score only eligible ready items. Rank cluster deficit first, then format deficit, evidence strength, explicit priority, and…
5. 5Reserve the selected item with a stable run ID. For --draft, invoke the writer without a publish time. Otherwise choose the next free…
6. 6Require review before any live publish or schedule mutation. Pass the topic scaffold and approved target to seo-blog-writer; do not copy…
7. 7Commit the state transition only after the downstream operation returns a durable draft ID, CMS ID, or explicit failure. Move ready ->…
8. 8For add, normalize the title and compare it with existing titles, slugs, canonical URLs, and distinctive error/version tokens. Add only…
9. 9For mark-done, require a matching live URL or an owner-approved manual receipt. For sync, preserve local notes while updating only fields…
10. 10Return the chosen work, schedule, state changes, conflicts, and next eligible slot. Leave failed or ambiguous items recoverable.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • WebSearch
  • WebFetch
  • Write
  • Edit

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • developers.google.com
  • docs.ghost.org
  • developer.wordpress.org
  • rfc-editor.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code; scheduling, publication, CMS reconciliation, and backlog mutation require the content owner's approval and current platform access

  From compatibility in the SKILL.md frontmatter.

Context cost

Blog Editorial Calendar loads about 1.8k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 782 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~76

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT-0 licence (© jeremylongshore). 782 words, ~1,843 tokens.

name

blog-editorial-calendar

description

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".

allowed-tools

Read, WebSearch, WebFetch, Write, Edit

compatibility

Designed for Claude Code; scheduling, publication, CMS reconciliation, and backlog mutation require the content owner's approval and current platform access

argument-hint

[status|next|add|mark-done|sync] [options]

version

1.1.0

author

AutomateLab <hello@automatelab.tech>

license

MIT-0

tags

seo, editorial-calendar, content-operations, scheduling, backlog

model

inherit

effort

high

{
  "id": "topic-0042",
  "title": "How to diagnose webhook signature failures",
  "cluster": "integrations",
  "format": "how-to-fix",
  "status": "ready",
  "priority": 2,
  "evidence_urls": ["https://example.com/verified-source"],
  "scheduled_at": null,
  "cms_id": null,
  "canonical_url": null
}

request: next 2 --draft --dry-run
result: topic-0042 (integrations deficit 0.08), topic-0017 (use-cases deficit 0.05)
mutation: none
next_slot_utc: 2026-09-12T06:00:00Z

request: sync
matched: topic-0042 -> cms_id=post_918 by canonical_url
transition: scheduled -> published
conflicts: 0

© jeremylongshore, MIT-0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in plugins/productivity/publishing-skills/skills/blog-editorial-calendar of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• backlog.json
• config.json

Open the folder on GitHubat commit cfae287