技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
codex-goals【数据与研究】Patterns and anti-patterns for using OpenAI Codex Goals — the persistent objectives feature introduced in Codex 0.128.0. Use this skill whenever writing, reviewing, or debugging a `/goal` invocation, deciding whether a task should be a Goal at all, drafting a research Goal that needs an evidence ledger, or diagnosing a Goal that completed against the…
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
/goal invocation, deciding whether a task should be a Goal at all, drafting a research Goal that needs an evidence ledger, or diagnosing a Goal that completed against the wrong surface. Triggers on /goal, "Codex Goal", "Codex goals", "persistent objective", "evidence-based completion", "iteration policy", "blocked stop condition", or any user message describing a multi-turn Codex task with a defined finish line. Trigger even if the user doesn't explicitly mention Goals — if they're typing "/goal" or asking Codex to "keep going until X", this skill applies.Reference for writing and managing Codex Goals — the persistent objective feature introduced in Codex 0.128.0. "Best practices" here means the patterns and anti-patterns that determine whether a Goal completes against the right evidence vs. silently against the wrong surface. Contains 31 rules across 8 categories, ordered by how much they affect whether a Goal completes correctly. Derived from the official OpenAI cookbook article "Using Goals in Codex".
Reference these guidelines when:
/goal or a normal prompt/goal invocation| Priority | Category | Impact (worst rule) | Prefix |
|---|---|---|---|
| 1 | Goal Fit Decisions | CRITICAL | fit- |
| 2 | Outcome Definition | CRITICAL / HIGH | outcome- |
| 3 | Verification Surface | CRITICAL / HIGH | verify- |
| 4 | Boundaries & Iteration | HIGH | bound- |
| 5 | Lifecycle Commands | HIGH | life- |
| 6 | Evidence-Based Completion | HIGH | evidence- |
| 7 | Crafting Strong Goals | MEDIUM | craft- |
| 8 | Research Goals & Anti-Patterns | MEDIUM | research- |
Individual rule impacts are listed inline in the per-rule frontmatter.
fit-when-to-use — Use a Goal When the Finish Line Is Clear but the Path Is Uncertainfit-three-required-properties — Require Three Properties Before Setting a Goal — Durable Objective, Evidence Finish Line, Multi-Turn Pathfit-prompt-vs-goal — Choose a Prompt for Single-Turn Work, a Goal for Outcome-Driven Continuationfit-skip-for-vague-targets — Skip a Goal When the Finish Line Is Vagueoutcome-measurable-end-state — State the Outcome as a Measurable End State, Not an Activityoutcome-quantify-thresholds — Pin Thresholds with Numbers, Not Relative Comparativesoutcome-narrow-but-discoverable — Make the Outcome Narrow Enough to Audit, Broad Enough to Allow Discoveryoutcome-name-the-artifact — For Generated Artifacts, Name the Artifact and Its Validity Conditionsverify-name-the-surface — Always Name the Verification Surface Inside the Goalverify-include-constraints — Include Constraints That Must Not Regress Alongside the Primary Metricverify-multiple-checks-when-needed — Use Multiple Verification Surfaces When a Single Check Is Insufficientverify-surface-must-be-runnable — The Verification Surface Must Be Something Codex Can Actually Run or Inspectbound-tools-and-files — Bound the Files, Tools, and Repositories Codex May Usebound-iteration-policy — Define an Iteration Policy — How Codex Chooses the Next Experiment Between Turnsbound-blocked-stop-condition — Define a Blocked Stop Condition — What to Report When No Defensible Path Remainsbound-respect-budget — Treat the Budget Limit as Halt-and-Summarize, Not Extendlife-set-with-slash-goal — Set a Goal with /goal <text> — Available from Codex 0.128.0life-pause-during-detours — Pause the Goal Before Unrelated Detours, Resume When Returninglife-clear-stale-goals — Clear Stale Goals on Resumed Threadslife-inspect-with-slash-goal — Use Bare /goal to Inspect Current Objective and State Before Continuationevidence-audit-before-completion — Audit the Objective Against Concrete Evidence Before Marking a Goal Completeevidence-budget-is-not-completion — Reaching the Budget Limit Is Not the Same as Completing the Objectiveevidence-honest-blockers — Surface Blockers Explicitly — Never Substitute a Proxy for the Asked Claimcraft-six-components — Define Six Components in Every Strong Goal — Outcome, Verification, Constraints, Boundaries, Iteration Policy, Blocked Stopcraft-template-pattern — Use the Canonical "verified by … while preserving … Use … Between iterations … If blocked …" Patterncraft-let-codex-draft-it — Ask Codex to Draft the Goal from a Plain-Language Description, Then Tightencraft-strengthen-weak-goals — Strengthen a Weak Goal by Naming the End State, Verification Surface, and Constraintsresearch-define-evidence-standard-first — For Research Goals, Define the Evidence Standard Before Investigation Beginsresearch-build-claim-inventory — Decompose Research Goals into a Claim Inventory Mapped to Evidence Channelsresearch-preserve-epistemic-ledger — Final Report Must Preserve Epistemic Levels Per Claim — Use a Structured Ledger Entryresearch-anti-patterns — Avoid the Three Common Goal Anti-Patterns — Keep-Going Wishes, Hidden Uncertainty, Overclaim on ProxyRead individual reference files for detailed explanations and worked examples comparing weak vs strong Goal text:
Each rule file contains:
| File | Description |
|---|---|
| AGENTS.md | Compiled TOC built by build-agents-md.js |
| references/_sections.md | Category definitions and impact ordering |
| assets/templates/_template.md | Template for new rules |
| metadata.json | Version and reference information |
| gotchas.md | Failure points discovered through use |