Skip to content

Roni-quant/goal-first

Repository files navigation

goal-first

Interrogate the decision before the artifact. The requested dashboard might really be an alert, a report, or a deleted process.

A scoping skill for Claude Code — goal interview, a one-page charter, then agile buckets with testable completion conditions that hand straight off to the built-in /goal command.

Version Claude Code plugin License: MIT GitHub stars PRs welcome

What you get

  • Goal interview — surfaces the recurring decision the artifact is meant to drive before any tech/data/feature talk.
  • One-page charter — goal, core decision, today's pain, a testable success signal, anti-goals, and buckets. Confirmed before any code.
  • Agile buckets — smallest decision-moving slice first, hard review checkpoint after each, no marching ahead unsolicited.
  • /goal handoff — every bucket carries a tool-verifiable "Done when", so a confirmed bucket drops straight into the autonomous /goal command.
  • Drift checks — every added scope must trace back to the core decision, out loud.

Why

  • The artifact is a hypothesis, not the goal. "Build me a dashboard" is a guess at a solution. The goal is the decision it serves. Build the wrong thing well = wasted work.
  • Solution questions come last. Asking "what stack? where's the data? which features?" first presumes the artifact is correct. This skill forbids those until the charter is confirmed.
  • Clarity feeds autonomy. The built-in /goal command runs autonomously until a completion condition is met — but it skips the WHAT/WHY interview. goal-first does that interview, then produces the precise, testable finish-line /goal needs.

Install

Plugin marketplace (recommended)

/plugin marketplace add Roni-quant/goal-first
/plugin install goal-first@goal-first-marketplace

Manual (Claude Code)

git clone https://github.com/Roni-quant/goal-first ~/.claude/skills-src/goal-first
ln -s ~/.claude/skills-src/goal-first/skills/goal-first ~/.claude/skills/goal-first

Try it

Send any of these to Claude Code and watch what goal-first does:

You say goal-first does
Build me a dashboard for our sales data. Stops. Runs the goal interview — what decision does the dashboard drive? — before any chart.
I need a Slack bot that posts daily metrics. Asks what action the daily post is meant to trigger; maybe the answer is an alert, not a feed.
Add a CSV export button to the report page. Well-defined edit → no interview, just builds it.

The product: the artifact never gets built until the decision behind it is written down and confirmed.

How it works

Every "build me X" request goes through this loop:

  1. User names an artifact to build.
  2. goal-first runs the goal interview — outcome, core decision, pain, success signal, anti-goal. No solution questions allowed.
  3. Writes PROJECT_CHARTER.md with a testable success signal and a bucket table.
  4. Checkpoint zero — confirm the charter before any code.
  5. Deliver the riskiest bucket first; checkpoint after each; never march ahead.
  6. Any confirmed bucket with a tool-verifiable "Done when" can hand off to /goal for autonomous execution.
  7. Drift check at every choice — scope that doesn't trace to the core decision gets named, not absorbed.

For a full transcript, see Examples.

goal-first and /goal

They're complementary, not competing:

/goal (built-in) goal-first
Job Execute autonomously until a completion condition is met Find the goal + decision, scope into buckets
Needs A precise, testable finish-line A vague "build me X" request
Skips The WHAT/WHY interview Nothing — it is the interview
Output Finished work, self-checked A charter + buckets, each with a /goal-ready Done-when

goal-first produces the finish-line /goal consumes. Use goal-first to scope, then hand each confirmed bucket to /goal to build.

Philosophy

  • Decision > artifact. Most "build me X" requests are solving the wrong X.
  • Confirm before code. A one-page charter is cheaper than a wrong build.
  • Testable or it doesn't ship. "Works well" is not a completion condition.
  • Checkpoints are hard stops. Agile means reviewed slices, not a big-bang plan.

Examples

Roadmap

See ROADMAP.md for v0.2, v0.3, v1.0 plans and out-of-scope notes.

Support

Questions, bug reports, scoping gaps: open an issue.

Contributing

See CONTRIBUTING.md. Short version: changes to the interview or charter shape need a transcript showing the gap they close.

Credits

  • anthropics/skills — single-repo plugin+marketplace pattern.
  • Claude Code's built-in /goal command — the autonomous-execution counterpart this skill feeds.
  • Roni-quant/skill-radar — repo structure this one mirrors.

License

MIT — see LICENSE.

About

Goal-first scoping skill for Claude Code: interrogate the decision before the artifact, write a one-page charter, deliver in testable buckets that hand off to /goal.

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors