Official agent skill

Examples Run Analysis

by openai in openai/openai-agents-js

Analyze logs and source from a completed repository example run.

OfficialMITAuto-check passed

Install Examples Run Analysis

skills CLI
$ npx skills add openai/openai-agents-js --skill examples-run-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openai/openai-agents-js examples-run-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openai/openai-agents-js.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/examples-run-analysis .claude/skills/examples-run-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
examples-run-analysis
GitHub stars
3.9k
Token cost
~1.1k tokens
SKILL.md length
629 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Analyze logs and source from a completed repository example run.

  • Works in 3 steps: Find the newest completed… → For every final table row with passed… → Read the runner sources…
  • SKILL.md covers Read-only boundary, Evidence to inspect, Evidence freshness and… and Required analysis, plus 1 more section
  • Calls pnpm

What it does

Examples Run Analysis is an agent skill from openai/openai-agents-js, published by the product's own GitHub organization. Analyze logs and source from a completed repository example run. Never execute or control examples.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It works with OpenAI and pnpm. The repository describes itself as: A lightweight, powerful framework for multi-agent workflows and voice agents. The licence is MIT.

Example prompts

  • “/examples-run-analysis”

Requirements

  • Node.js

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Find the newest completed .tmp/examples-start-logs/main_*.log. A completed main log contains the final Done. line, validation summary, All…
  2. For every final table row with passed and exit 0, resolve the full package:script name from the earlier start or skip lines when the…
  3. Read the runner sources scripts/run-examples-workflow.sh and scripts/run-example-starts.mjs when needed to interpret filters, auto-input…

What it can do on your machine

Read from SKILL.md and the folder at commit d8fa6c3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Examples Run Analysis loads about 1.1k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 629 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from openai/openai-agents-js at commit d8fa6c3, republished under its MIT licence (© openai). 629 words, ~1,135 tokens.

Download SKILL.mdSave it as .claude/skills/examples-run-analysis/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
examples-run-analysis
description
Analyze logs and source from a completed repository example run. Never execute or control examples.

Examples Run Analysis

Use this skill only to analyze evidence produced by a completed manual example workflow. The repository workflow belongs to the contributor who invoked its pnpm command; this skill never owns execution or cleanup.

Read-only boundary

  • Use only read-only file listing, reading, and searching to inspect repository sources and existing evidence.
  • Never invoke pnpm, Node.js, Bash, an example, a build, a test, or another workflow command.
  • Never start, rerun, retry, stop, signal, or kill a process. Never create or own a background job.
  • Never request elevated execution, broaden filesystem or network authority, source shell startup files, or alter credentials.
  • Never create, modify, rename, or delete a log, rerun list, result file, source file, PID file, or other repository path.
  • Do not treat this skill as authorization to perform a missing run. Ask the user to run the appropriate pnpm command manually and return after completed evidence exists.

Evidence to inspect

  1. Find the newest completed .tmp/examples-start-logs/main_*.log. A completed main log contains the final Done. line, validation summary, All start results: heading, table header, and one final table row for every discovered entry in that run. Treat a log without that complete footer as incomplete or still running.
  2. For every final table row with passed and exit 0, resolve the full package:script name from the earlier start or skip lines when the fixed-width table abbreviated it. Read the matching .tmp/examples-start-logs/<package>__<script>.log and the example's package.json script target plus its relevant source files.
  3. Read the runner sources scripts/run-examples-workflow.sh and scripts/run-example-starts.mjs when needed to interpret filters, auto-input, concurrency, serialized entries, configured exclusions, auto-skips, optional server/audio/external modes, and timeouts.

Evidence freshness and completeness

Do not analyze a run as current when any of these conditions applies:

  • no main log exists;
  • the newest main log lacks its complete footer or indicates cancellation;
  • its result table cannot be reconciled with the starts and skips recorded earlier in that same log;
  • an exit-zero row has no matching non-empty per-example log or its full identity cannot be resolved;
  • source files relevant to the requested validation changed after the run;
  • the PID file or log evidence indicates that a workflow is still active;
  • the available log predates the run or revision the user asked about.

When evidence is missing, stale, incomplete, or still running, stop the analysis and ask the user to run or finish pnpm examples:workflow:start manually. Mention optional flags such as --filter, --include-server, --include-audio, or --include-external only when they match the user's requested scope. Do not run the command yourself.

Show full SKILL.md (213 more words)Show less

Required analysis

Analyze every entry, not a sample.

  • For every exit-zero example, compare its intended flow in source and comments with its log. Confirm the meaningful actions and results occurred, such as expected tool calls, approvals, handoffs, streamed output, generated artifacts, or final messages. Exit code zero alone is not behavioral validation.
  • Classify non-zero entries as a repository failure, an expected example-level failure, an external dependency or credential restriction, a host/environment restriction, or incomplete evidence. Quote the concise untruncated log lines that justify the classification.
  • Classify every skip by its recorded reason: interactive, server, audio, external service, default auto-skip, conditional missing environment, or runner exclusion. Distinguish an intentional skip from a failure and from an environment restriction.
  • Report configured filters and optional modes so the user can see the exact scope that was and was not exercised.

Output

Begin with whether the completed run is behaviorally valid for its recorded scope. Then provide one concise line per example with its classification and evidence. Include a separate list of failures, intentional skips, and environment restrictions when any exist. For a valid exit-zero entry, name what was checked rather than saying only passed.

Do not omit or ellipsize the log lines that establish a conclusion. Keep excerpts short, but include each relevant line in full.

© openai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/examples-run-analysis of openai/openai-agents-js.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit d8fa6c3

Compare with similar skills

Examples Run Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Examples Run Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Examples Run Analysis this skillopenai/openai-agents-js3.9k—~1.1kAutomated safety check: PassMIT
KrillinAI CLI Operatorkrillinai/OpenCreator13k—~869Automated safety check: PassApache-2.0
DevSpace Manual QA SetupWaishnav/devspace5.2k—~440Automated safety check: PassMIT
Check Deps SyncHyk260/PureChat546—~594Automated safety check: PassMIT
Fix PR Design Notesdifferent-ai/openwork24k—~824Automated safety check: PassCustom licence
Geo Fundamentalswasp-lang/wasp19k8 repos~861Automated safety check: PassMIT

Similar skills

  • KrillinAI CLI Operator

    krillinai/OpenCreator

    Routes agents to the right KrillinAI command for subtitles, dubbing, video rendering, covers and speech, and explains how to read its JSON and manifest output.

    13k GitHub stars~869 tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • DevSpace Manual QA Setup

    Waishnav/devspace

    Prepares the current DevSpace checkout or worktree for isolated local manual QA, covering QA state seeding, UI asset builds and snapshot resets.

    5.2k GitHub stars~440 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Check Deps Sync

    Hyk260/PureChat

    Check if package.json files are in sync with pnpm-lock.yaml.

    546 GitHub stars~594 tokensUpdated 20 days ago
    DevOps & CloudAuto-check passed
  • Fix PR Design Notes

    different-ai/openwork

    Reads the advisory design review attached to a pull request's screenshots, fixes the flagged UI problems in product code, and proves each note is gone.

    24k GitHub stars~824 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Geo Fundamentals

    wasp-lang/wasp

    Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).

    19k GitHub starsUsed in 8 repos~861 tokens
    Marketing & SEOAuto-check passed
  • AI SDK

    vercel-labs/ai-facts

    Official

    Answer questions about the AI SDK and help build AI-powered features.

    168 GitHub starsUsed in 21 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

More from openai/openai-agents-js

All 10 skills in this repo
  • Changeset Validation

    openai/openai-agents-js

    Official

    Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes).

    3.9k GitHub stars~607 tokensUpdated today
    Auto-check passed
  • Pnpm Upgrade

    openai/openai-agents-js

    Official

    Keep pnpm current: preflight the published package and pnpm/action-setup self-installer, update pnpm locally, align packageManager in package.json, and refresh CI pins.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Final Release Review

    openai/openai-agents-js

    Official

    Assess a JS SDK release candidate or release plan against the previous release and recommend ship or block.

    3.9k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Sensitive Logging Audit

    openai/openai-agents-js

    Official

    Audit or fix sensitive-data exposure in JS SDK diagnostics, exceptions, logging, and telemetry.

    3.9k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Runtime Behavior Probe

    openai/openai-agents-js

    Official

    Plan and, after explicit approval, execute runtime-behavior probes for local or live integrations.

    3.9k GitHub stars~4.9k tokensUpdated today
    Auto-check passed
  • Code Change Verification

    openai/openai-agents-js

    Official

    Run the required final install, build, type, lint, test, and format checks after eligible SDK changes pass review.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Works with

Questions about Examples Run Analysis

What does Examples Run Analysis do?

Analyze logs and source from a completed repository example run. Examples Run Analysis is an agent skill from openai/openai-agents-js, published by the product's own GitHub organization. Analyze logs and source from a completed repository example run.

How do I install Examples Run Analysis in Claude Code?

Run `npx skills add openai/openai-agents-js --skill examples-run-analysis -a claude-code`. Or copy the skill folder (.agents/skills/examples-run-analysis in openai/openai-agents-js) into .claude/skills/examples-run-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Examples Run Analysis in Codex?

Run `npx skills add openai/openai-agents-js --skill examples-run-analysis -a codex`. Or copy the skill folder (.agents/skills/examples-run-analysis in openai/openai-agents-js) into .agents/skills/examples-run-analysis in your project. Codex loads it when a task matches its description.

Can I use Examples Run Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openai/openai-agents-js --skill examples-run-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/examples-run-analysis, .gemini/skills/examples-run-analysis, .github/skills/examples-run-analysis and .opencode/skills/examples-run-analysis in your project.

What does Examples Run Analysis need to run?

Going by SKILL.md and its folder, Examples Run Analysis needs the command-line tools its instructions call (pnpm). Our summary lists: Node.js.

Does Examples Run Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Examples Run Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Examples Run Analysis use?

Examples Run Analysis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Examples Run Analysis use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Examples Run Analysis?

Skills that share tags, products or a category with Examples Run Analysis: KrillinAI CLI Operator (krillinai/OpenCreator, 13k stars), DevSpace Manual QA Setup (Waishnav/devspace, 5.2k stars), Check Deps Sync (Hyk260/PureChat, 546 stars) and Fix PR Design Notes (different-ai/openwork, 24k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Examples Run Analysis?

openai (a GitHub organization, an official publisher) maintains it in openai/openai-agents-js, which has 3,892 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 6, 2026.

Source: openai/openai-agents-js on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.