Agent skill
implementation-strategy
Decide how to implement runtime and API changes in openai-agents-js before editing code. Use when a task changes exported APIs, runtime behavior, schemas, tests, or docs and you need to choose the compatibility boundary, whether shims or migrations are warranted, and when unreleased interfaces can be rewritten directly.
Install this agent skill to your Project
npx add-skill https://github.com/openai/openai-agents-js/tree/main/.agents/skills/implementation-strategy
SKILL.md
Implementation Strategy
Overview
Use this skill before editing code when the task changes runtime behavior or anything that might look like a compatibility concern. The goal is to keep implementations simple while protecting real released contracts and genuinely supported external state.
Quick start
- Identify the surface you are changing: released public API, unreleased branch-local API, internal helper, persisted schema, wire protocol, CLI/config/env surface, or docs/examples only.
- Determine the latest release boundary from
originfirst, and only fall back to local tags when remote tags are unavailable:bashLATEST_RELEASE_TAG="$( git ls-remote --tags --refs origin 'v*' 2>/dev/null | awk -F/ '{print $3}' | sort -V -r | head -n1 )" if [ -z "$LATEST_RELEASE_TAG" ]; then LATEST_RELEASE_TAG="$(git tag -l 'v*' --sort=-v:refname | head -n1)" fi printf '%s\n' "$LATEST_RELEASE_TAG" - Judge breaking-change risk against that latest release tag, not against unreleased branch churn or post-tag changes already on
main. If the command fell back to local tags, treat the result as potentially stale and say so. - Prefer the simplest implementation that satisfies the current task. Update callers, tests, docs, and examples directly instead of preserving superseded unreleased interfaces.
- Add a compatibility layer only when there is a concrete released consumer, an otherwise supported durable external state that requires it, or when the user explicitly asks for a migration path.
Compatibility boundary rules
- Released public API or documented external behavior: preserve compatibility or provide an explicit migration path.
- Persisted schema, serialized state, wire protocol, CLI flags, environment variables, and externally consumed config: treat as compatibility-sensitive once they are released or otherwise have a supported external consumer. Unreleased post-tag formats that only exist on the current branch can still be rewritten directly.
- Interface changes introduced only on the current branch: not a compatibility target. Rewrite them directly.
- Interface changes present on
mainbut added after the latest release tag: not a semver breaking change by themselves. Rewrite them directly unless they already back a released or otherwise supported durable format. - Internal helpers, private types, same-branch tests, fixtures, and examples: update them directly instead of adding adapters.
Default implementation stance
- Prefer deletion or replacement over aliases, overloads, shims, feature flags, and dual-write logic when the old shape is unreleased.
- Do not preserve a confusing abstraction just because it exists in the current branch diff.
- If review feedback claims a change is breaking, verify it against the latest release tag and actual external impact before accepting the feedback.
- If a change truly crosses the latest released contract boundary, call that out explicitly in the ExecPlan, changeset, and user-facing summary.
When to stop and confirm
- The change would alter behavior shipped in the latest release tag.
- The change would modify durable external data or protocol formats that are already released or otherwise supported.
- The user explicitly asked for backward compatibility, deprecation, or migration support.
Output expectations
When this skill materially affects the implementation approach, state the decision briefly in your reasoning or handoff, for example:
Compatibility boundary: latest release tag v0.x.y; branch-local interface rewrite, no shim needed.Compatibility boundary: latest release tag v0.x.y; unreleased RunState snapshot rewrite, no shim needed.Compatibility boundary: released RunState schema; preserve compatibility and add migration coverage.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
openai-knowledge
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
final-release-review
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-js.
examples-auto-run
Run examples:start-all in auto mode with parallel execution, per-script logs, and start/stop helpers.
docs-sync
Analyze main branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Only update English docs (docs/src/content/docs/**) and never touch translated docs under docs/src/content/docs/ja, ko, or zh. Provide a report and ask for approval before editing docs.
pnpm-upgrade
Keep pnpm current: run pnpm self-update/corepack prepare, align packageManager in package.json, and bump pnpm/action-setup + pinned pnpm versions in .github/workflows to the latest release. Use this when refreshing the pnpm toolchain manually or in automation.
runtime-behavior-probe
Plan and execute runtime-behavior investigations with temporary TypeScript probe scripts, validation matrices, state controls, and findings-first reports. Use only when the user explicitly invokes this skill to verify actual runtime behavior beyond normal code-level checks, especially to uncover edge cases, undocumented behavior, or common failure modes in local or live integrations. A baseline smoke check is fine as an entry point, but do not stop at happy-path confirmation.
Didn't find tool you were looking for?