chatgpt-apps
OfficialScaffold and refactor ChatGPT Apps SDK projects that pair an MCP server with a widget UI.
Agent & orchestration
Turns a fuzzy intention into a measurable objective with named evidence and scope bounds before work starts.
Restates what the user wants as a single objective string that names the outcome, the artifact or system involved, how completion is verified, what is in and out of scope, and when to stop and ask. It makes goals quantitative where the domain allows — exact test commands, thresholds like p95 latency, artifact constraints, or evidence counts — and rewrites or rejects activity goals such as "make progress." Before creating anything it calls get_goal to check for an existing goal, then calls create_goal only if the objective passes the quality bar.
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.
Confirm that goal definition is actually needed.
$define-goal, asks to create or set a goal, asks for the goal tool, or wants help turning an intention into a clear objective.Restate the likely goal in concrete terms. A usable goal names:
Make it quantitative when the domain supports it. Prefer numbers that represent real success, not decorative precision:
Repair weak goals before setting them.
Check active goal state before creating a goal.
get_goal.create_goal.Create the goal only after it passes the quality bar.
create_goal for an ordinary multi-step task unless the user explicitly asked for goal-backed work.Before create_goal, the objective should answer:
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.
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:
If the user cannot provide a metric, propose the most honest binary validator available and ask for confirmation.
Scaffold and refactor ChatGPT Apps SDK projects that pair an MCP server with a widget UI.
Build or update full Figma screens from code or a description by reusing the file's published design system.
Builds a Figma design system from your codebase in staged, checkpointed phases.
Run JavaScript against the Figma Plugin API to create, edit, and inspect nodes in a Figma file.
Turn a concept, brand cue, or reference image into a validated 8x9 Codex pet atlas with QA sheets and pet.json packaging.
Generate or edit raster images inside your project, from hero shots and sprites to transparent-background cutouts.