From code
Extracts markdown from plan.json content field and syncs to plan.md. Required after any plan.json edit; triggers on sync requests or JSON-to-markdown conversion.
How this skill is triggered — by the user, by Claude, or both
Slash command
/code:extract-plan-mdThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Sync plan.md with plan.json content. **Use this skill after ANY edit to plan.json.**
Sync plan.md with plan.json content. Use this skill after ANY edit to plan.json.
REQUIRED after plan.json edits:
Also use for:
To sync plan.md with plan.json. The scripts/ directory is relative to this skill's base directory (shown above as "Base directory for this skill"):
python3 <base_directory>/scripts/extract.py /path/to/plan.json
The script:
content key (which contains the full markdown plan)\n -> actual newlines)plan.md in the same directory as the plan.jsonAfter editing plan.json, sync plan.md:
python3 <base_directory>/scripts/extract.py .closedloop-ai/work/plan.json
# Updates .closedloop-ai/work/plan.md to match
Extract from a specific plan:
python3 <base_directory>/scripts/extract.py ~/work/plan.json
# Creates/updates ~/work/plan.md
npx claudepluginhub closedloop-ai/claude-plugins --plugin codeDefines conventions for editing plan.json implementation plans, including task formats (T-X.Y IDs, complexity S/M/L), structured arrays, JSON escaping, and plan structure rules. Use when creating or modifying plan.json files.
Tracks task completion in markdown plan files using plan-file-management subcommands. Mandates test verification of observables and evidence before marking tasks done. Activates on *-plan.md files.
Executes tasks from PLAN.md sequentially with human oversight, handling task splitting, clarifying questions, tests, and learning persistence. Useful for deliberate progress on planned work.