agentleFS
Sign inStart free
wedabrowedabro/bro-skills/.agents/skills/speckit.backlog/SKILL.md

speckit.backlog

Skill3 starsChanged 45 days agoMITView on GitHub

Backlog Manager - Manage Ideas, Pending Requests and scan TODO/FIXME from codebase.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read .agents/memory/constitution.md, existing backlog files (.agents/backlog/IDEAS.md, TECHNICAL_DEBT.md), recent specs, and codebase …

    line 10
  2. Distinctive:

    Ensure priority changes have explicit rationale.

    line 25
  3. Distinctive:

    DO NOT arbitrarily delete the backlog without asking the user.

    line 31
  4. Distinctive:

    DO NOT overflow the context by listing thousands of TODOs.

    line 32
  5. Distinctive:

    DO NOT mark items resolved without verified test, review, or user acceptance evidence.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Mission

Organize, triage, and prioritize unfulfilled requirements, technical debt, and prospective features, ensuring no ideas or defect signals are lost during long-term development.

Inputs and Outputs

  • Read .agents/memory/constitution.md, existing backlog files (.agents/backlog/IDEAS.md, TECHNICAL_DEBT.md), recent specs, and codebase search results.
  • Preserve stable item IDs, maintain prioritization rationale, and record dated state transitions when promoting or resolving items.

Protocol

1. Intake & Deduplication

  • Capture problem statement, user value, reproducibility evidence, affected component, priority, and clear acceptance criteria.
  • Deduplicate against existing items by linking related IDs; categorize as Feature Idea, Bug, Technical Debt, or Security Risk. Never silently discard an item.

2. Automated Debt & Marker Scan

  • Scan targeted scope for source markers (TODO:, FIXME:, HACK:, BUG:) using rg; record file, line number, actionable context, and severity.
  • Persist scanned debt findings in .agents/backlog/TECHNICAL_DEBT.md with timestamp and query command.

3. Grooming & Promotion

  • Periodically review stale or blocked backlog items, establish minimal next actionable steps, and promote ready items to formal feature specs (spec.md).
  • Ensure priority changes have explicit rationale; never close or mark items resolved without verified test or acceptance evidence.

Completion Gate

Backlog entries are categorized with stable IDs, technical debt logs reflect current codebase reality, and promoted items link to corresponding specifications.

Guard Rails

  • DO NOT arbitrarily delete the backlog without asking the user.
  • DO NOT overflow the context by listing thousands of TODOs. Only list tasks related to the area you are working on.
  • DO NOT mark items resolved without verified test, review, or user acceptance evidence.

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.

Reviews can't be read right now.

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.

Check your setup, free