Delegate independent tasks to specialized agents working concurrently with isolated context.
Skillset Smoke Test Runner
skillset-smoke-test
Run and evaluate the Skillset smoke test (aliases, sets, and skill invocation) and interpret its JSON reports. Use this when validating $skill/$set behavior or checking Claude Code/Codex headless runs.
SKILL.md
Full skill instructions
Skillset Smoke Test Runner
Keep this skill self-contained. If you need more detail, read REFERENCE.md.
Prereqs
- Ensure
bunis available. - For full runs, ensure
claudeandcodexCLIs are installed and authenticated. - Run from the repo root so the smoke test can find
scripts/skillset-smoke.ts.
Run the smoke test
- Prefer the repo script so results are structured and gitignored.
- Quick smoke (hook-only):
bun run test:smoke:ci
- Hook-only (CLI mode):
bun run test:smoke:cli
- Full run (hook + Claude + Codex):
bun run test:smoke
Options
--tools hook,claude,codexto limit which tools run.--hook-mode ci|clito choose the hook path (repeatable or comma-separated).--no-cleanto preserve the sandbox workspace and XDG dirs.--clean-allto wipe all smoke test artifacts (workspace + reports).--strictto exit non-zero if any step fails.
Environment overrides
SKILLSET_SMOKE_CLAUDE_CMD(default:claude)SKILLSET_SMOKE_CLAUDE_ARGS(extra args)SKILLSET_SMOKE_CODEX_CMD(default:codex)SKILLSET_SMOKE_CODEX_ARGS(extra args)
Interpret results
- Reports live under
.skillset-smoke/reports/<runId>/report.json. - Check
steps[*].statusandsteps[*].details.evidencefor sentinel hits. - When a step fails, inspect its
stdoutPath/stderrPathfor errors.- Hook steps are labeled
hook-ciandhook-cli. - The smoke test cleans by default; re-run with
--no-cleanto keep state for debugging.
- Hook steps are labeled
Triage checklist
Use this checklist in order when a run fails or evidence is missing:
- Open the report JSON and find the first
steps[*].status !== "ok". - If
stdoutPath/stderrPathexist, read them for the error message. - Confirm the workspace and XDG paths in the report (they must be under
.skillset-smoke/). - If a tool step is
skipped, verify the CLI is installed and auth is valid. - If
hookevidence is missing for a set, confirm the set resolves inset-loadand re-run--tools hookto isolate hook output issues. - If sentinels are missing for skills, confirm the smoke test created fixtures in
.skillset-smoke/workspace/.claude/skills. - Re-run with
--tools hookto isolate local resolution issues before retrying full runs.
Notes
- Outputs are stored under
.skillset-smoke/and are gitignored. - If the
.codex/skillssymlink is missing, re-create it to mirror this skill.
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
