agentleFS
Sign inStart free
notquenotque/vexjoy-agent/skills/content/series-planner/SKILL.md

series-planner

Skill448 starsChanged 5 days agoMITView on GitHub

Plan multi-part content series: structure, cross-linking, cadence.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check viability: minimum 3 distinct subtopics, each stands alone, logical progression exists, no filler.

    line 55
  2. Distinctive:

    No critical info deferred to other parts

    line 75
  3. Distinctive:

    Search landing on this part alone yields value

    line 76
  4. Distinctive:

    Gate: All parts pass standalone test.

    line 82
  5. Distinctive:

    Every part has standalone value

    line 90
  6. Distinctive:

    No cliff-hangers, no filler

    line 93
  7. Distinctive:

    Gate: All checks pass. Plan complete.

    line 97

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Series Planner Skill

Plan multi-part content series: assess viability, select structure, produce plan with cross-linking and cadence. Three phases with strict gates.

Deep References

SignalLoadWhy
Publishing frequency, delay handlingreferences/cadence-guidelines.mdSchedule selection criteria
Navigation links, Hugo implementationreferences/cross-linking.mdPrev/next nav, shortcodes, landing pages
Plan output formatreferences/output-format.mdComplete plan template
Series types, selection matrixreferences/series-types.mdThree type templates with examples

Usage

/series [topic]
/series --type=progressive [topic]     # Force type
/series --parts=5 [topic]              # Target count
/series --with-landing [topic]         # Include landing page
/series --minimal [topic]              # Titles and scope only

Phase 1: ASSESS

Determine viability and natural divisions.

  1. Analyze topic: scope (narrow/medium/broad), natural divisions, audience progression.
  2. Check viability: minimum 3 distinct subtopics, each stands alone, logical progression exists, no filler.
  3. Detect series type:
SignalType
learn, master, deep diveProgressive Depth
build, create, projectChronological Build
why we chose, migration, debuggingProblem Exploration

Gate: 3+ natural divisions identified. If fewer, recommend single post or scope adjustment.

Phase 2: DECIDE

Select type, part count (strict 3-7 bounds), and structure.

  1. Select type and justify. Define part count and word estimate.
  2. Draft breakdown per part: title, scope (1 sentence), standalone value, adjacent links.
  3. Validate standalone value for every part:
    • Reader learns something complete and actionable from this part alone
    • Working code/config/output possible without other parts
    • No critical info deferred to other parts
    • Search landing on this part alone yields value

Red flags (reject): "read Part 1 first" dependency, mid-implementation endings, concepts only in earlier parts.

  1. Select cadence (see references/cadence-guidelines.md). Default: weekly.

Gate: All parts pass standalone test. Part count 3-7. Type justified.

Phase 3: GENERATE

Produce the complete plan.

  1. Build plan: series header, per-part breakdown, cross-linking (see references/cross-linking.md), publication dates, Hugo frontmatter.
  2. Final validation checklist:
    • Every part has standalone value
    • Word counts 800-1500/part, within 20% variance
    • Cross-linking complete (prev/next for all)
    • No cliff-hangers, no filler
    • Part count within bounds
  3. Output using references/output-format.md format.

Gate: All checks pass. Plan complete.

Series Types

TypeStructureReader flexibility
Progressive DepthShallow to deep masteryBeginners stop at Part 1; advanced skip ahead
Chronological BuildStep-by-step creationEach part produces working output
Problem ExplorationProblem to solution journeyEven failed approaches are instructive

Error Handling

ErrorCauseSolution
Topic too narrowFewer than 3 natural divisionsRecommend single post or scope expansion
Topic too broadWould need 8+ partsSplit into multiple series; narrow scope
No logical progressionParts are loosely related, not buildingConsider standalone posts instead of series
Standalone value missingParts depend on each otherMerge dependent parts or add context inline

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free