BC blog-editorial-calendar
Run your blog like a queue, not a guessing game. This skill is the orchestration layer on top of blog-topic-research and seo-blog-writer: it keeps an evidence-backed backlog, picks the next topic so your corpus drifts toward the cluster + format mix you defined, schedules posts into a rolling daily cadence, and marks them done — autonomously, two posts a day if you want. It scores every pick by how far each topic cluster is from its target weight (so you never end up with 40 troubleshooting posts and no comparisons), reconciles the backlog against what's actually live on your CMS, and auto-refills by calling blog-topic-research when the queue runs dry. Platform-agnostic: it drives whatever publish adapter seo-blog-writer is configured for (Ghost, WordPress, static site). Built for founders, indie hackers, and content teams who want a hands-off long-tail SEO pipeline that publishes on a schedule and stays balanced. Trigger when the user says: 'what should I write next', 'pick the next topic', 'schedule the next N posts', 'editorial calendar status', 'add this to the backlog', 'mark this post done', or any variant of running a recurring publish cadence.
Run your blog like a queue, not a guessing game.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1169 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 35 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4849 tokens
- 85Steps. 32 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 13 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1169: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 18 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.