agentleFS
Alter-aiAlter-ai/skill-lab/skills/backlog/SKILL.md

backlog

Skill0 starsChanged 10 days agoMITView on GitHub

Keeps a solo developer's Scrum backlog in BACKLOG.md - product goal, user stories with acceptance criteria, MoSCoW priority, WBS, weekly schedule with a Gantt chart, Definition of Done, and sprint goal, review and retrospective. Use when starting a project, planning or closing a sprint, writing user stories or a WBS, picking the next item to build, or producing a schedule or Gantt chart for a report.

39 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use issue, worktree and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AWSSkill

    issue

    Implement a GitHub issue end-to-end — branch, code, test, docs, and commit.

    Also in 3 projects that use this

  • MicrosoftSkill

    worktree

    Create, reuse or clean up a dedicated git worktree for working on a pull request or a private branch. Use from any PR-scoped workflow that needs an isolated checkout to keep current code and build output untouched.

    Also in 3 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 4 projects that use this

  • HashiCorpSkill

    changelog

    Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • VercelSkill

    deploy

    Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 5

    Distinctive

    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. Distinctive:

    Keep: a Product Goal, an ordered backlog, fixed-length sprints (1-2 weeks), a Sprint Goal, a Definition of Done, and a review plus …

    line 12
  2. Very specific:

    If the problem or users are unclear, use user-research and competitive-brief first.

    line 20
  3. Distinctive:

    Check INVEST: independent, negotiable, valuable, estimable, small (fits one sprint), testable.

    line 25
  4. Distinctive:

    Write the Sprint Goal as one sentence of user-visible outcome.

    line 30
  5. Distinctive:

    Update 時程 if dates moved, and regenerate the chart.

    line 37
  6. Distinctive:

    Run from the skill directory against the project's file:

    line 40

“Common” is measured: kept by at least 6 in 10 of the 38 edited versions of this file we could read. “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

Backlog (solo Scrum)

One file, BACKLOG.md at the repo root, is the product backlog, sprint board and schedule. Start it from assets/BACKLOG.template.md.

Solo adaptation of Scrum

Keep: a Product Goal, an ordered backlog, fixed-length sprints (1-2 weeks), a Sprint Goal, a Definition of Done, and a review plus retrospective at each sprint end. Drop: daily stand-ups, story points, burndown charts, role ceremonies. One person holds Product Owner, Scrum Master and Developer at once. Limit work in progress to 2 items. Finishing beats starting.

Workflows

New project

  1. Copy the template to BACKLOG.md. Fill Product Goal and the first stories from the user's brief.
  2. If the problem or users are unclear, use user-research and competitive-brief first; record findings as evidence under the story they support.
  3. Draft the WBS and the 時程 table. Generate the chart (below). Ask the user to confirm priorities before any build work.

Writing a story

  • Format: 身為<角色>,我希望<能力>,以便<價值>.
  • Check INVEST: independent, negotiable, valuable, estimable, small (fits one sprint), testable.
  • Acceptance criteria as Given / When / Then, each one checkable by a test or a demo step.
  • Priority: Must / Should / Could / Won't (this release). The MVP is the Must set only.

Sprint start

  1. Write the Sprint Goal as one sentence of user-visible outcome.
  2. Pull the top Must items that fit; move them to 進行中.
  3. Hand each item to superpowers:brainstorming (CLAUDE.md rule 1), then superpowers:writing-plans. The story's acceptance criteria become the plan's tests.

Sprint end

  1. Review: for each item, Done only if every Definition of Done line holds. Otherwise it returns to the backlog with what is left.
  2. Retrospective: three lines - kept, change, try. A correction the user made twice becomes a proposed Gotcha; ask the user before adding it to CLAUDE.md or a skill.
  3. Update 時程 if dates moved, and regenerate the chart.

Gantt chart

Run from the skill directory against the project's file:

uv run --isolated --no-project --python 3.13 --with matplotlib python scripts/gantt.py <repo>/BACKLOG.md <repo>/docs/gantt.png

The script reads only the ## 時程 table (columns 項目 | 開始 | 結束 | 里程碑, dates YYYY-MM-DD; any text in 里程碑 draws a diamond). It stops with the row number on a bad date or an end before the start: fix the table, never hand-draw the chart.

Gotchas

  • uv run without --isolated --no-project picks up a parent .venv, and that environment may have a different Python or broken packages.
  • matplotlib needs a CJK font for Chinese labels; the script asks for Microsoft JhengHei first.
  • A course or client template may fix the report sections; keep BACKLOG.md as the source and copy from it into the report, not the reverse.

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.