Define a measurable goal
Turns a fuzzy intention into one measurable goal with a validator, scope and stop condition, then registers it via get_goal and create_goal. Use before goal-backed or long-running agent work, when "done" needs a number or a check.
define-goal- Author
- OpenAI
- Source
- openai/skills/skills/.curated/define-goal @ 49f948f
- License
- Apache-2.0
About this skill
What it does
The skill turns a vague intention into one objective an agent can be held to, then registers it with the agent's goal tool. By its rules a usable goal names the outcome that will be true, the artifact or system involved, how completion is verified, what is in and out of scope, and when to stop and ask instead of grinding on.
Where the domain allows, the goal gets numbers: an exact test command and pass condition, a latency threshold with measurement method and run count, the allowed blast radius, counts of verified cases. Activity goals such as "keep investigating" or "improve things" are rejected until they are sharpened. Sample goals show the bar: p95 under 250 ms across three benchmark runs is good, "make checkout faster" is weak.
If a missing detail would change the outcome, the agent asks one short question; otherwise it rewrites the goal itself. Before creating anything it calls get_goal: a matching active goal is reused, a conflicting one makes the agent ask. Only then does it call create_goal with a single objective string that includes the evidence. The skill writes no plans, logs or other files.
When to use it, and when not
Use it before goal-backed or long-running agent work, or whenever you want "done" settled before the agent starts.
For ordinary implementation requests the skill itself says to skip it.
How to run it
The install command below puts the folder in place: SKILL.md, the Codex metadata file and the licence. The skill calls get_goal and create_goal, tools of the host agent; where they do not exist, you get the goal text but nothing is registered. To call it:
- Claude Code:
/define-goal, or ask for the skill by name. - Codex:
$define-goal. - Cursor: type
/in the Agent chat and pickdefine-goal.
Example: /define-goal I want the flaky e2e suite fixed before the release.
OpenAI has marked openai/skills deprecated; our copy is pinned to a commit there, and as of November 2026 openai/plugins has no newer version of this skill.
How it differs from similar skills
Interview me pins down intent through a longer interview, one question per message, ending in a statement you confirm with an explicit yes. Spec-first kickoff and Spec-driven development go on to a written spec and a build plan. This skill stops at one measurable sentence and the goal tool call. Verification before completion works at the other end: it checks the evidence before the agent says "done".
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/define-goal/SKILL.md https://anymodel.org/en/skills/openai/define-goal/SKILL.md -o ~/.claude/skills/define-goal/LICENSE.txt https://anymodel.org/en/skills/openai/define-goal/LICENSE.txt -o ~/.claude/skills/define-goal/agents/openai.yaml https://anymodel.org/en/skills/openai/define-goal/agents/openai.yaml
curl -fsSL --create-dirs -o ~/.agents/skills/define-goal/SKILL.md https://anymodel.org/en/skills/openai/define-goal/SKILL.md -o ~/.agents/skills/define-goal/LICENSE.txt https://anymodel.org/en/skills/openai/define-goal/LICENSE.txt -o ~/.agents/skills/define-goal/agents/openai.yaml https://anymodel.org/en/skills/openai/define-goal/agents/openai.yaml
foreach ($f in 'SKILL.md','LICENSE.txt','agents/openai.yaml') { $p = Join-Path "$HOME\.claude\skills\define-goal" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/openai/define-goal/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE.txt','agents/openai.yaml') { $p = Join-Path "$HOME\.agents\skills\define-goal" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/openai/define-goal/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/openai/define-goal/SKILL.md
SKILL.md
Define Goal
Overview
Shape the user's intent into an objective an agent can pursue honestly. Prefer measurable outcomes, explicit evidence, and bounded scope over activity descriptions.
This skill covers goal definition and goal-tool creation only. Do not create intermediate planning artifacts, durable snapshots, ledgers, decision logs, or resume files from this skill.
Workflow
Confirm that goal definition is actually needed.
- Use this skill when the user asks for
$define-goal, asks to create or set a goal, asks for the goal tool, or wants help turning an intention into a clear objective. - If the user only asks for ordinary implementation work, do the work directly instead of forcing goal creation.
- Use this skill when the user asks for
Restate the likely goal in concrete terms. A usable goal names:
- the specific outcome that will be true
- the main artifact, system, repo, environment, or user-facing behavior involved
- how completion will be verified
- what is in scope
- what is out of scope when ambiguity would matter
- the stop condition for asking the user instead of grinding
Make it quantitative when the domain supports it. Prefer numbers that represent real success, not decorative precision:
- pass/fail validators: exact tests, checks, CI jobs, evals, commands, or acceptance criteria
- quality thresholds: latency, error rate, cost, accuracy, recall, precision, coverage, flake rate, bundle size, memory, uptime, completion rate, or manual review criteria
- artifact constraints: file paths, affected modules, allowed commands, output formats, target environments, deadlines, or maximum blast radius
- evidence counts: number of reproduced failures, successful reruns, reviewed examples, migrated records, addressed comments, or verified cases
Repair weak goals before setting them.
- Rewrite vague goals into measurable objectives when local context makes the rewrite safe.
- Ask one concise clarification question when the missing detail changes the intended outcome or validation.
- Reject pure activity goals such as "make progress," "keep investigating," "improve things," or "work on X" unless they are sharpened into a verifiable outcome.
Check active goal state before creating a goal.
- Call
get_goal. - If there is no active goal and the objective meets the quality bar, call
create_goal. - If there is an active goal that still matches the user's intent, continue using it instead of creating a duplicate.
- If there is an active goal that conflicts with the new request, ask whether to finish the current goal, mark it complete if done, or start a separate goal-backed thread.
- Call
Create the goal only after it passes the quality bar.
- Use a single concise objective string.
- Include the verification evidence in the objective itself.
- Include scope bounds when they constrain the work.
- Include a token budget only when the user explicitly requested one.
- Do not call
create_goalfor an ordinary multi-step task unless the user explicitly asked for goal-backed work.
Goal Quality Bar
Before create_goal, the objective should answer:
- What concrete thing will be true when this is done?
- What evidence will prove it?
- What quantitative or binary threshold defines success?
- What scope boundaries matter?
- What should cause the agent to stop and ask?
Good:
Reduce checkout API p95 latency below 250 ms for the documented slow path by making the smallest safe server-side change, then verify with
npm run test:checkoutand the existing local latency benchmark showing p95 under 250 ms across 3 consecutive runs.
Good:
Resolve the open review comments on PR 123 that request code changes, update only the affected auth files and tests, and verify with the targeted auth test command plus
gh pr view 123showing no unresolved change-request threads.
Weak:
Make checkout faster.
Weak:
Keep investigating the PR comments.
Quantification Heuristics
- For bugs, define success as reproduction first, fix second, and a failing-then-passing validator when possible.
- For tests, name the exact command and required pass condition.
- For performance, name the metric, target threshold, measurement method, and number of runs.
- For quality work, define an observable acceptance bar such as reviewed examples, lint/typecheck/test pass, or user-approved artifact.
- For research, define the decision the research must enable, the sources or systems in scope, and the evidence standard.
- For operations, define healthy state, monitoring window, failure threshold, and rollback or escalation trigger.
Clarifying Questions
Ask only when a reasonable rewrite would risk pursuing the wrong outcome. Keep the question short and oriented around the missing validator or scope boundary.
Useful question shapes:
- "What metric should define success here: latency, cost, accuracy, or user-visible behavior?"
- "Which environment should I verify against: local, staging, or production?"
- "What is the minimum evidence you want before I mark this goal complete?"
If the user cannot provide a metric, propose the most honest binary validator available and ask for confirmation.
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel