Manage editorial content through 6 pipeline stages.
npx skills add https://github.com/notque/vexjoy-agent --skill content-calendar
Manage editorial content through 6 pipeline stages: Ideas, Outlined, Drafted, Editing, Ready, Published. All pipeline state lives in a single content-calendar.md file -- this is the sole source of truth, never store state elsewhere.
| Signal | Load These Files | Why |
|---|---|---|
| calendar file location, template, section formats | calendar-format.md | Loads detailed guidance from calendar-format.md. |
| errors, error handling | error-handling.md | Loads detailed guidance from error-handling.md. |
| velocity tracking and stuck-content detection | metrics.md | Loads detailed guidance from metrics.md. |
| series planning: multi-part structure, cross-linking, cadence | series-planner.md | Series planning domain from folded series-planner skill. |
| topic brainstorming: problem mining, gap analysis, scoring | topic-brainstormer.md | Topic ideation domain from folded topic-brainstormer skill. |
| headlines: charge, volume, tighten, format adaptation | headlines.md | Headline generation domain from folded headlines skill. |
| content repurposing: platform-native social variants | content-engine.md | Content repurposing domain from folded content-engine skill. |
| news collection: item qualification, freshness forensics | news-collection.md | News collection domain from folded news-collection skill. |
| executing view, add, move, schedule, archive operations | operations.md | Loads detailed guidance from operations.md. |
| stage definitions and transition rules | pipeline-stages.md | Loads detailed guidance from pipeline-stages.md. |
Goal: Load and validate the current calendar state before any mutation.
Memory of pipeline state is unreliable -- always read the actual file, because assumed state leads to overwrites of changes made by other processes or manual edits.
content-calendar.md from the project root. Also read the repository CLAUDE.md to ensure compliance with project-specific rules.Gate: Calendar file loaded and parsed successfully. All sections accounted for. Proceed only when gate passes.
Goal: Perform the requested pipeline operation -- only the operation requested. No speculative reorganization, no "while I'm here" reformatting of unrelated sections.
- [ ] [Topic name] to Ideas sectionContent moves forward through defined stages only -- each transition represents real editorial work completed, so skipping stages misrepresents progress.
(outline: YYYY-MM-DD)(draft: YYYY-MM-DD)(editing: YYYY-MM-DD)(ready: YYYY-MM-DD) -- prompt for a scheduled publication date because content without a date clogs the pipeline and goes stale(published: YYYY-MM-DD)Scheduled: YYYY-MM-DD to entryArchive prevents the Published section from growing unbounded, which makes the dashboard cluttered and counts misleading.
### YYYY-MM section in HistoricalGate: Operation executed with all validations passing. Proceed only when gate passes.
Goal: Persist changes and verify the write succeeded.
Read the full calendar file before writing -- never truncate or lose existing entries.
Gate: File written, re-read confirms changes persisted. Operation complete.
Cause: content-calendar.md does not exist in the project
Solution:
Cause: User referenced a topic name that does not match any entry
Solution:
Cause: User attempted to skip a stage (e.g., Ideas directly to Ready)
Solution:
| Task | Load |
|------|------|
| Stage definitions, transition criteria | ${CLAUDE_SKILL_DIR}/references/pipeline-stages.md |
| File format, section structure, date fields | ${CLAUDE_SKILL_DIR}/references/calendar-format.md |
| Command reference, edge cases per operation | ${CLAUDE_SKILL_DIR}/references/operations.md |
| File not found, corrupt sections, count drift, malformed dates | ${CLAUDE_SKILL_DIR}/references/error-handling.md |
| Velocity metrics, stuck content, pipeline health dashboard | ${CLAUDE_SKILL_DIR}/references/metrics.md |
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take notque/content-calendar from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.