define-goal

Name: define-goal
Author: openai

24kstars1.6kforks

How to install define-goal?

openai/skills/define-goal

$npx -y skills add openai/skills --skill define-goal

Installs into the current project.

Summary

Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refine

Files · 1

View on GitHub

SKILL.md

1	# Define Goal
2
3	## Overview
4
5	Shape the user's intent into an objective an agent can pursue honestly. Prefer measurable outcomes, explicit evidence, and bounded scope over activity descriptions.
6
7	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.
8
9	## Workflow
10
11	1. Confirm that goal definition is actually needed.
12	- 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.
13	- If the user only asks for ordinary implementation work, do the work directly instead of forcing goal creation.
14
15	2. Restate the likely goal in concrete terms.
16	A usable goal names:
17	- the specific outcome that will be true
18	- the main artifact, system, repo, environment, or user-facing behavior involved
19	- how completion will be verified
20	- what is in scope
21	- what is out of scope when ambiguity would matter
22	- the stop condition for asking the user instead of grinding
23
24	3. Make it quantitative when the domain supports it.
25	Prefer numbers that represent real success, not decorative precision:
26	- pass/fail validators: exact tests, checks, CI jobs, evals, commands, or acceptance criteria
27	- quality thresholds: latency, error rate, cost, accuracy, recall, precision, coverage, flake rate, bundle size, memory, uptime, completion rate, or manual review criteria
28	- artifact constraints: file paths, affected modules, allowed commands, output formats, target environments, deadlines, or maximum blast radius
29	- evidence counts: number of reproduced failures, successful reruns, reviewed examples, migrated records, addressed comments, or verified cases
30
31	4. Repair weak goals before setting them.
32	- Rewrite vague goals into measurable objectives when local context makes the rewrite safe.
33	- Ask one concise clarification question when the missing detail changes the intended outcome or validation.
34	- Reject pure activity goals such as "make progress," "keep investigating," "improve things," or "work on X" unless they are sharpened into a verifiable outcome.
35
36	5. Check active goal state before creating a goal.
37	- Call `get_goal`.
38	- If there is no active goal and the objective meets the quality bar, call `create_goal`.
39	- If there is an active goal that still matches the user's intent, continue using it instead of creating a duplicate.
40	- 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.
41
42	6. Create the goal only after it passes the quality bar.
43	- Use a single concise objective string.
44	- Include the verification evidence in the objective itself.
45	- Include scope bounds when they constrain the work.
46	- Include a token budget only when the user explicitly requested one.
47	- Do not call `create_goal` for an ordinary multi-step task unless the user explicitly asked for goal-backed work.
48
49	## Goal Quality Bar
50
51	Before `create_goal`, the objective should answer:
52
53	- What concrete thing will be true when this is done?
54	- What evidence will prove it?
55	- What quantitative or binary threshold defines success?
56	- What scope boundaries matter?
57	- What should cause the agent to stop and ask?
58
59	Good:
60
61	> 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:checkout` and the existing local latency benchmark showing p95 under 250 ms across 3 consecutive runs.
62
63	Good:
64
65	> 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 123` showing no unresolved change-request threads.
66
67	Weak:
68
69	> Make checkout faster.
70
71	Weak:
72
73	> Keep investigating the PR comments.
74
75	## Quantification Heuristics
76
77	- For bugs, define success as reproduction first, fix second, and a failing-then-passing validator when possible.
78	- For tests, name the exact command and required pass condition.
79	- For performance, name the metric, target threshold, measurement method, and number of runs.
80	- For quality work, define an observable acceptance bar such as reviewed examples, lint/typecheck/test pass, or user-approved artifact.
81	- For research, define the decision the research must enable, the sources or systems in scope, and the evidence standard.
82	- For operations, define healthy state, mo

People who liked this also viewed

6 picks

Type

define-goal

24kstars1.6kforks

View on GitHub

How to install define-goal?

openai/skills/define-goal

$npx -y skills add openai/skills --skill define-goal

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Define Goal
2
3	## Overview
4
5	Shape the user's intent into an objective an agent can pursue honestly. Prefer measurable outcomes, explicit evidence, and bounded scope over activity descriptions.
6
7	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.
8
9	## Workflow
10
11	1. Confirm that goal definition is actually needed.
12	- 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.
13	- If the user only asks for ordinary implementation work, do the work directly instead of forcing goal creation.
14
15	2. Restate the likely goal in concrete terms.
16	A usable goal names:
17	- the specific outcome that will be true
18	- the main artifact, system, repo, environment, or user-facing behavior involved
19	- how completion will be verified
20	- what is in scope
21	- what is out of scope when ambiguity would matter
22	- the stop condition for asking the user instead of grinding
23
24	3. Make it quantitative when the domain supports it.
25	Prefer numbers that represent real success, not decorative precision:
26	- pass/fail validators: exact tests, checks, CI jobs, evals, commands, or acceptance criteria
27	- quality thresholds: latency, error rate, cost, accuracy, recall, precision, coverage, flake rate, bundle size, memory, uptime, completion rate, or manual review criteria
28	- artifact constraints: file paths, affected modules, allowed commands, output formats, target environments, deadlines, or maximum blast radius
29	- evidence counts: number of reproduced failures, successful reruns, reviewed examples, migrated records, addressed comments, or verified cases
30
31	4. Repair weak goals before setting them.
32	- Rewrite vague goals into measurable objectives when local context makes the rewrite safe.
33	- Ask one concise clarification question when the missing detail changes the intended outcome or validation.
34	- Reject pure activity goals such as "make progress," "keep investigating," "improve things," or "work on X" unless they are sharpened into a verifiable outcome.
35
36	5. Check active goal state before creating a goal.
37	- Call `get_goal`.
38	- If there is no active goal and the objective meets the quality bar, call `create_goal`.
39	- If there is an active goal that still matches the user's intent, continue using it instead of creating a duplicate.
40	- 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.
41
42	6. Create the goal only after it passes the quality bar.
43	- Use a single concise objective string.
44	- Include the verification evidence in the objective itself.
45	- Include scope bounds when they constrain the work.
46	- Include a token budget only when the user explicitly requested one.
47	- Do not call `create_goal` for an ordinary multi-step task unless the user explicitly asked for goal-backed work.
48
49	## Goal Quality Bar
50
51	Before `create_goal`, the objective should answer:
52
53	- What concrete thing will be true when this is done?
54	- What evidence will prove it?
55	- What quantitative or binary threshold defines success?
56	- What scope boundaries matter?
57	- What should cause the agent to stop and ask?
58
59	Good:
60
61	> 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:checkout` and the existing local latency benchmark showing p95 under 250 ms across 3 consecutive runs.
62
63	Good:
64
65	> 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 123` showing no unresolved change-request threads.
66
67	Weak:
68
69	> Make checkout faster.
70
71	Weak:
72
73	> Keep investigating the PR comments.
74
75	## Quantification Heuristics
76
77	- For bugs, define success as reproduction first, fix second, and a failing-then-passing validator when possible.
78	- For tests, name the exact command and required pass condition.
79	- For performance, name the metric, target threshold, measurement method, and number of runs.
80	- For quality work, define an observable acceptance bar such as reviewed examples, lint/typecheck/test pass, or user-approved artifact.
81	- For research, define the decision the research must enable, the sources or systems in scope, and the evidence standard.
82	- For operations, define healthy state, mo

People who liked this also viewed

6 picks

Type