agentleFS
juanitourquizajuanitourquiza/shipframe/skills/planning-features/SKILL.md

planning-features

Skill4 starsChanged 21 days agoMITView on GitHub

Run feature discovery and plan-expert together for a new feature, producing ticket and subtask structure.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run the full feature-discovery skill as defined in its SKILL.md:

    line 16
  2. Distinctive:

    Ask the user if they want to create a ClickUp ticket

    line 20
  3. Very specific:

    After create-task completes, capture TICKET_ID and TICKET_URL from its output

    line 24
  4. Distinctive:

    Do not continue or suggest further steps.

    line 58

≈ “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

planning-features

You are a feature planning orchestrator. You execute two skills in sequence in this context. The skills are preloaded — execute their instructions directly, do not spawn subagents.

Execution Steps

Step 1 — Execute the feature-discovery skill

Run the full feature-discovery skill as defined in its SKILL.md:

  • Collect the initial feature description (from the user's message or by asking)
  • Complete all three questioning phases
  • Present the final spec and get user confirmation
  • Ask the user if they want to create a ClickUp ticket

If the user agrees to create a ClickUp ticket:

  • The feature-discovery skill will delegate to create-task to handle template selection, filling, and creation
  • After create-task completes, capture TICKET_ID and TICKET_URL from its output

If the user declines:

  • Store the full confirmed feature spec markdown as FEATURE_SPEC
  • Set TICKET_ID to null

Step 2 — Execute the plan-expert skill

Run the full plan-expert skill as defined in its SKILL.md:

If TICKET_ID is available: execute with --ticket-id <TICKET_ID>

If TICKET_ID is null: execute with --description "<FEATURE_SPEC>" — pass the entire confirmed feature spec markdown, not a summary.


Step 3 — Finish

Once plan-expert has completed and all subtasks have been created, output this summary and stop:

## Planning Complete

**Feature:** <feature name>
**ClickUp Ticket:** <TICKET_URL if available, otherwise "not created">
**Ticket ID:** <TICKET_ID if available, otherwise "n/a">
**Subtasks created:** <count>

The feature has been fully documented and broken into an execution plan.
Your team can now pick up individual subtasks and begin implementation.

Do not continue or suggest further steps.

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.