agentleFS
samwelmungasamwelmunga/jenga-npm/.agents/skills/j-spinoff/SKILL.md

j.spinoff

Skill0 starsChanged 22 days agoApache-2.0View on GitHub

Capture a diverging topic mid-conversation. Collects context and a mandatory origin, optionally runs /brainstorm for prerequisites, saves an /idea entry, and returns focus to the primary thread.

The file

Files
SKILL.md

Spinoff — Capture a Diverging Topic

skills/j-spinoff/ is the canonical, hand-edited directory for this skill, per CLAUDE.md's "The Canonical Naming Contract" (the E50 reopening of 2026-09-09, which promoted skills/j-spinoff/ from generated twin to sole canonical form). The j- prefix is there for collision safety — a real directory under a distinct name, so a host tool shipping its own same-named built-in command cannot shadow it (Claude Code's native skill resolution is a literal-string, directory-name-based match; see project/documentation/skill-authoring.md's "Invocation Convention").

⚠️ scripts/generate-j-alias.sh was retired by E50_S14 and no longer exists — there is nothing to run. This file was previously generated from a bare skills/spinoff/SKILL.md source; E50_S15 deleted that directory. This file is now the sole canonical, hand-edited source for this skill — edit it directly.

Instructions

  1. Identify the diverging topic — Ask the user to confirm or briefly describe the diverging topic.
    • Pre-fill the prompt with a one-sentence summary of what the agent detected as the diverging subject (if known).
    • Example: "It looks like we started discussing [detected topic]. Is that the diverging thread you'd like to capture, or would you like to describe it differently?"
  2. Collect context — Summarise the relevant context gathered so far in the current conversation that relates to the diverging topic. This summary will pre-fill the /idea description so no context is lost.

    Capture the Origin (mandatory) — Record:

    • The EST id (task, story, or epic) that was in progress when the divergence happened, if any is currently being worked. If none is in progress (e.g. the divergence happened during a /brainstorm-only session with no active EST item), use None — this is a valid, expected case, not a gap to fill in later.
    • A one-line summary of what the user was doing at the time of the divergence.
  3. Check prerequisites — Ask the user:

    "Are the requirements for [diverging topic] clear enough to act on, or would you like to run /brainstorm first to flesh them out?"

    Offer these choices:

    • "Requirements are clear — save now" → go to step 5
    • "Run /brainstorm first" → go to step 4
  4. Run /brainstorm (if chosen) — Invoke the /brainstorm skill, passing the diverging topic and collected context as the opening prompt. After /brainstorm completes, use the refined output as the idea description.
  5. Save via /idea — Populate skills/j-idea/assets/idea_handoff_template.md with the context collected so far:

    • Mission title: the diverging topic name (as confirmed in step 1)
    • Goal / objective: what the diverging topic aims to achieve
    • Affected files or scope: any files or modules identified during the conversation
    • Intended approach: the context/approach collected in step 2 (or the refined output from step 4)
    • Epic/Story linkage: include a reference if a relevant Epic or Story was identified, otherwise None
    • Origin: the EST id (or None) and one-line context summary captured in step 2

    Then invoke the /idea skill with the populated template. Since the template fields are pre-filled, /idea will skip any questions already answered. The entry lands in project/ideas.md, not project/todo.md — /spinoff no longer writes to the todo list directly.

  6. Return focus — Inform the user:

    "✅ Diverging topic saved as an idea. Returning focus to [primary topic]."

    Then resume the primary conversation thread exactly where it was paused.

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.