agentleFS
degdeg/beads-utils/skills/defer/SKILL.md

defer

Skill2 starsChanged 6 days agoMITView on GitHub

Defer (park) a bead — set it aside without closing it. TRIGGER whenever the user asks to defer, park, shelve, postpone, snooze, sideline, punt, set aside, or push off a bead/issue/task, or says "not now" / "later" / "revisit after X". NEVER `bd close` to park — closing destroys discoverability.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. denolfe/dotfiles★ 88same name
    2. cstrlcs/skills★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    If no bead ID is given, ask which bead to defer.

    line 15
  2. Very specific:

    Run bd show <id> to load its current state.

    line 16
  3. Very specific:

    If the trigger is a point in time ("next quarter", "after the credit review"), convert it to a concrete YYYY-MM-DD for --until.

    line 22
  4. Distinctive:

    If the trigger is an *evidence condition* with no timeline ("if profiling shows X"), use no date — capture the condition in the reason …

    line 23
  5. Distinctive:

    Wait for explicit go. Do not write until the user approves.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Defer (park) a bead

Set a bead aside so it leaves bd ready but stays discoverable, recording why and (optionally) when to revisit. This is the standard "parking" mechanism.

MANDATORY: Deferring is the ONLY park mechanism. NEVER use bd close to park a task — closing is destructive to discoverability and hides priority. Only close if the user explicitly asks to close (not "park", "shelve", "set aside", or "defer"). When in doubt, defer.

1. Identify the bead

  • The argument may be a bead ID, optionally followed by free-text context (a reason, a date). Parse what you can from it.
  • If no bead ID is given, ask which bead to defer.
  • Run bd show <id> to load its current state. If it is already closed, confirm the user wants it reopened-and-deferred before proceeding.

2. Gather the two inputs (DISCUSS ONLY — no writes yet)

  • Reason — why set it aside now, and the concrete trigger/condition that would justify reviving it. Write it self-contained: it must make sense months later, read cold, without this conversation. This becomes the defer_reason metadata field. Keep it to one or two sentences: the gate for revisiting, not the plan for what to do then — that belongs in the bead's body.
  • Wake date — either a specific calendar date, or none:
    • If the trigger is a point in time ("next quarter", "after the credit review"), convert it to a concrete YYYY-MM-DD for --until.
    • If the trigger is an evidence condition with no timeline ("if profiling shows X"), use no date — capture the condition in the reason instead.

3. Confirm before writing

  • Show the proposed defer_reason wording and the wake date (or "no date").
  • Wait for explicit go. Do not write until the user approves.

4. Apply (only after go)

  • bd defer <id> [--until=YYYY-MM-DD]
  • bd update <id> --set-metadata defer_reason="<the approved reason>"
  • Single source of truth: the reason lives ONLY in defer_reason metadata. Do not also pass --reason / append it to notes — that duplicates it and drifts.

5. Verify + user- and project-specific steps

  • Extensions are read from two places, user first, then project, and both are followed: ~/.claude/skill-extensions/defer.md, then .claude/skill-extensions/defer.md in the project.
  • Otherwise, verify with bd show <id>: status should be deferred, and the METADATA section should show defer_reason.

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.