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

j.idea

Skill0 starsChanged 22 days agoApache-2.0View on GitHub

Capture a loosely-defined idea to project/ideas.md — a lightweight, "maybe someday" log with no board or promotion overhead.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Keep this light — /idea is a low-overhead capture, not a structured mission intake like /todo.

    line 34
  2. Distinctive:

    If another — go back to step 2.

    line 42
  3. Very specific:

    No agent invoked by /idea applies terminal (PROMOTED/REJECTED) tags or acts on them — that is reserved for the promotion step (e.g.

    line 103

≈ “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

Idea — Lightweight Idea Capture

skills/j-idea/ 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-idea/ 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/idea/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. Ensure project/ideas.md exists — If it doesn't exist, it will be auto-created by idea_manager.sh from skills/j-idea/assets/idea_template.md — no manual action needed.
  2. Ask the user about the idea:

    • What's the idea?
    • Any known context worth noting (why it came up, what it might relate to)?

    Keep this light — /idea is a low-overhead capture, not a structured mission intake like /todo.

  3. Add to project/ideas.md by running:
    bash "$([ -f scripts/idea_manager.sh ] && echo scripts/idea_manager.sh || echo node_modules/@jenga-ai/agent/scripts/idea_manager.sh)" add '<idea>'
  4. Ask the user: "Capture another idea, or done?"

    • If another — go back to step 2.
    • If done — exit.

    Unlike /todo, /idea never offers to execute, refine, or promote the captured idea(s) at the end. There is no /do-style follow-up here — /idea has no refine or promotion logic of its own.

For Reference Only — Promotion Convention (not implemented here)

/idea does not implement any refine or promotion mechanism. This section documents, for reference, how promotion is expected to work elsewhere so future flows stay consistent:

  • Promoting an idea means re-running /brainstorm on it, which routes onward to /btw or /todo as normal. That routing behavior already exists and is out of scope for /idea.
  • Terminal idea states are marked directly in project/ideas.md using the same HTML-comment tag convention project/todo.md uses for RECONCILED:
    • PROMOTED — the idea was picked up via /brainstorm and turned into board work.
    • REJECTED — the idea was reviewed and dropped.

Embedded Board ID

PROMOTED/REJECTED tags support an embedded board ID, so the idea→board-item link is machine-readable directly from the tag itself, without needing a separate lookup:

  • <!-- PROMOTED: E##_S##[_T##] --> — the _T## task suffix is optional; use whichever level the idea was actually promoted into (an epic, a story, or a specific task).
  • <!-- REJECTED --> — stays bare, with no embedded ID. A rejection has no resulting board item to point at.

Example (mirroring project/todo.md's tagging style):

Add dark mode toggle to settings page <!-- PROMOTED: E12_S03 -->
Add a settings-page keyboard shortcut cheat sheet <!-- PROMOTED: E12_S03_T02 -->
Rewrite onboarding copy in a more casual tone <!-- REJECTED -->

Source-Rapport Link Convention

Some ideas originate from a rapport rather than being manually captured via /idea — e.g. when scrum-master's rapport_review step (E35_S03) detects a distinct idea surfaced inside a problem rapport and, on user confirmation, appends it to project/ideas.md the same way /idea does. When that happens, the entry's source rapport is recorded with a second inline HTML comment on the same line:

<!-- rapport: <path/to/rapport.md> -->

Rules:

  • Written at capture time, alongside the idea text, by whichever flow is adding the entry (scrum-master's rapport-derived capture path; /idea's own manual capture never has a source rapport and omits this comment entirely).
  • Left in place through promotion/rejection — the rapport: comment and the terminal PROMOTED/REJECTED comment coexist on the same line, e.g.:
    Extract shared retry logic into a utility <!-- rapport: project/rapports/problems/E40_S02_T01-segment-remarks.md --> <!-- PROMOTED: E61_S01 -->
  • Consumed by the outcome-record mechanism at promotion/rejection time: if a rapport: comment is present on the line, that rapport is updated with the decision (and [SPIKE]-prefixed in its title/header if not already, per templates/SCRUM_BOARD_SCHEMA.md's [SPIKE] section); if absent (a manually-captured /idea entry with no source rapport), a project/documentation/plans/<slug>_PROMOTED.md or _REJECTED.md file is created instead.
  • Verified compatible with scripts/idea_manager.sh's real_entries() filtering: that function only strips lines whose first non-whitespace characters are <!--; a trailing inline comment on an otherwise real entry line is untouched and the line still counts as a real entry.

No agent invoked by /idea applies terminal (PROMOTED/REJECTED) tags or acts on them — that is reserved for the promotion step (e.g. within /brainstorm) and, for rapport-sourced ideas, scrum-master's rapport-review flow.

Outcome-Record Mechanism (idea_manager.sh) — E35_S03_T03

scripts/idea_manager.sh implements the tagging and outcome-record behavior described above, via four additional subcommands beyond add/list:

  • tag "<idea-text>" <PROMOTED:E##_S##[_T##]|REJECTED> — writes the terminal tag onto the project/ideas.md line matching <idea-text> (an exact/literal match; errors if zero or more than one line matches, and errors if the line is already tagged).
  • get-id "<idea-text>" — prints the embedded board ID from that line's PROMOTED tag (errors if the line has no PROMOTED tag).
  • get-rapport "<idea-text>" — prints the rapport: path recorded on that line, or nothing (exit 0) if the line has no source-rapport comment.
  • resolve "<idea-text>" <promoted|rejected> [board_id] — the full outcome-record mechanism in one call: tags the line (as tag does), then either updates the idea's source rapport or, if none is recorded, creates the project/documentation/plans/ fallback file:

    • Source rapport present: the rapport's # Rapport: ... title line is prefixed [SPIKE] if not already, and an ## Idea Outcome Record section (decision, date, resulting board ID if promoted, and the idea text) is appended to the rapport file.
    • No source rapport: project/documentation/plans/<slug>_PROMOTED.md or _REJECTED.md is created (idea text slugified, lowercased, capped at 60 characters), containing the same decision/date/board-ID/idea-text content.

    board_id is required for promoted (validated to start with E<digits>) and must be omitted for rejected (a rejection has no resulting board item).

This is the mechanism itself, not the trigger — nothing currently calls resolve automatically. A future promotion step (e.g. within /brainstorm's routing, or scrum-master acting on a rapport-sourced idea) is expected to invoke it once that trigger exists.

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.