Goal Setter
Turns a rough request into a compact, evidence-bound /goal for long autonomous coding runs.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 18, 2026 · d752cf9
Asked to draft a /goal for endpoint rate-limiting, the skill refused to let the objective collapse into a numbered step list and instead forced one evidence-bound paragraph (429 after the 10th request in 60s, npm test must stay green) -- exactly the failure mode it names and bans ('Build UI, add API, write tests is a plan; it is not Done').
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What Goal Setter does
Drafts, audits, and activates a /goal that pins down Done, verification evidence, scope boundaries, and stop conditions, built for multi-iteration Codex or Claude Code work rather than one-off edits. Explicitly declines to fire on ordinary implementation, Q&A, or subjective work with no rubric, and ships a bundled length-validator script to keep the goal under the runtime's character cap.
How to install Goal Setter
git clone https://github.com/gotalab/goal-setter-skill
cd goal-setter-skill
mkdir -p ~/.claude/skills
cp -r skills/goal-setter ~/.claude/skills/goal-setter
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Goal Setter
-
/goal-setterTurns a rough request into a compact, evidence-bound /goal for long autonomous coding runs.
It also activates on plain-language prompts like these:
-
Draft a goal for the agent to keep working until tests pass. -
Help me scope out an autonomous coding task with clear success criteria. -
Audit this task description, is it well-defined for a long agent run?
Frequently asked questions
- Is the Goal Setter skill free?
- Yes. The skill itself is free from gotalab/goal-setter-skill. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Goal Setter work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Asked to draft a /goal for endpoint rate-limiting, the skill refused to let the objective collapse into a numbered step list and instead forced one evidence-bound paragraph (429 after the 10th request in 60s, npm test must stay green) -- exactly the failure mode it names and bans ('Build UI, add API, write tests is a plan; it is not Done').
- What is the Goal Setter SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Goal Setter?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Goal Setter with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.