{ "markdown": "
\n \"@workersio/skills\n
\n\n

Skills to find unknown bugs before release!

\n\n

\n We help your agents test edge cases in your software where rare production bugs hide.\n

\n\n

\n \"License\"\n \"Stars\"\n

\n\nMost AI-written tests optimize for coverage. They assert implementation details,\nmock away the real risk, and pass even when the product breaks.\n`@workersio/skills` gives coding agents a testing workflow that asks a stricter\nquestion: will this test catch a real regression that users, operators,\nreviewers, or maintainers care about?\n\n`@workersio/skills` is one skill with five command modes:\n\n```text\n$wio scan # Find high-value tests to add next.\n$wio test # Run candidate discovery, strategy, implementation, and review.\n$wio workload # Generate realistic, replayable workloads with new bug-finding value.\n$wio review # Judge whether a test should be kept, redone, or removed.\n$wio doctor # Audit suite health, weak assertions, flakes, mocks, and CI blind spots.\n```\n\n## Works With\n\n

\n \n \n \"Codex\"\n   \n \n \n \"Claude\n   \n \n \n \"Cursor\"\n   \n \n \n \"GitHub\n   \n \n \n \"Gemini\"\n \n

\n\n`@workersio/skills` is packaged for Codex and Claude Code today. The core skill\ncontent is plain Markdown, so the testing workflow can also be adapted by other\ncoding agents that support project skills, instructions, or reusable prompts.\n\n## Install\n\nDirect skill install:\n\n```bash\nnpx skills add workersio/skills\n```\n\nCodex plugin marketplace:\n\n```bash\ncodex plugin marketplace add workersio/skills\n```\n\nClaude Code plugin marketplace:\n\n```bash\nclaude plugin marketplace add workersio/skills\nclaude plugin install wio@workersio-skills\n```\n\nFor local Codex plugin testing from this checkout:\n\n```bash\ncodex plugin marketplace add .\n```\n\n## What It Provides\n\n| Area | What the agent gets |\n| --- | --- |\n| Test discovery | Maps product behavior, recent changes, existing tests, CI, and risk areas before choosing what to test. |\n| Strategy selection | Chooses the right level: unit, component, integration, contract, E2E, workload, fuzz, property, mutation, resilience, or monitoring. |\n| Test writing | Adds focused tests using the repository's own framework, naming, fixtures, helpers, and runner conventions. |\n| Workload generation | Creates realistic, adversarial, seeded, replayable sessions or traffic that add coverage beyond wrappers and parameter sweeps. |\n| Test review | Applies a strict value gate: `KEEP`, `REDO`, or `REMOVE`. Coverage alone is not enough. |\n| Suite health | Finds weak assertions, over-mocking, broad snapshots, flakes, skipped tests, slow feedback loops, and CI blind spots. |\n\n## Command Guide\n\n| Command | Use it when | Example |\n| --- | --- | --- |\n| `$wio scan [target]` | You do not yet know what to test. | `$wio scan checkout` |\n| `$wio test [target]` | You want the full write-and-review loop. | `$wio test billing eligibility regression` |\n| `$wio workload [target]` | The risk lives in realistic user, API, CLI, job, or load behavior. | `$wio workload onboarding session` |\n| `$wio review [target]` | A test exists and you need to decide whether it has real value. | `$wio review tests/billing_eligibility_test.py` |\n| `$wio doctor [target]` | The suite is hard to trust or maintain. | `$wio doctor API test suite` |\n\n## Quality Bar\n\nAn approved test should answer:\n\n- What user, operator, customer, or API consumer failure does this prevent?\n- What production, release, support, debugging, or review risk does it reduce?\n- Would it fail for the regression that matters?\n- Which assertion or invariant catches the plausible bug?\n- Does the setup preserve the important dependency, state, permission, timing, or data risk?\n- Does this belong in local development, PR CI, nightly, release, or production monitoring?\n- If this is a workload, what existing workload gap does it fill?\n\nIf those answers are weak, the test should be redesigned or removed.\n\n## Subagents\n\n`@workersio/skills` includes three optional focused subagents:\n\n| Subagent | Role |\n| --- | --- |\n| `wio-candidate-scout` | Read-only discovery of high-value test candidates before implementation. |\n| `wio-strategy-critic` | Read-only challenge of the selected strategy before editing tests. |\n| `wio-test-reviewer` | Read-only post-write review that returns `KEEP`, `REDO`, or `REMOVE`. |\n\nThe main agent still writes the test and owns the final decision. Subagents\ninspect, challenge, and review; they do not duplicate the reference library or\nreplace the main workflow.\n\n## Repository Layout\n\n| Path | Purpose |\n| --- | --- |\n| `plugins/wio/skills/wio/SKILL.md` | Source of truth for the skill workflow. |\n| `plugins/wio/skills/wio/references/` | Detailed testing guidance loaded only when relevant. |\n| `plugins/wio/agents/` | Claude Code plugin subagents. |\n| `.codex/agents/` | Codex custom-agent TOML files for project or user installs. |\n| `plugins/wio/hooks/hooks.json` | Shared plugin hook config. |\n| `.agents/plugins/marketplace.json` | Codex marketplace entry. |\n| `.claude-plugin/marketplace.json` | Claude Code marketplace entry. |\n| `public/` | README assets, demo GIF, and agent icons. |\n\n## Codex Agents And Hooks\n\nCodex plugin installs include the skill and plugin hook config. Codex custom\nagents are a separate native surface loaded from `.codex/agents/` in a project\nor `~/.codex/agents/` for the user.\n\nEnable the Codex agents globally:\n\n```bash\nmkdir -p ~/.codex/agents\ncp .codex/agents/wio-*.toml ~/.codex/agents/\n```\n\nEnable the Codex agents for the current project:\n\n```bash\nmkdir -p .codex/agents\ncp /path/to/wio-skills/.codex/agents/wio-*.toml .codex/agents/\n```\n\nEnable the Codex hook config for the current project:\n\n```bash\nmkdir -p .codex\ncp /path/to/wio-skills/.codex/hooks.json .codex/hooks.json\n```\n\n## Claude Code Agents And Hooks\n\nClaude plugin installs include the skill, plugin hooks, and Markdown\nsubagents from `plugins/wio/agents/`. Project-local Claude Code agents can also\nbe copied into `.claude/agents/` when a repository is not using the plugin.\n\n## References\n\nDetailed testing guidance lives only in\n`plugins/wio/skills/wio/references/`. Reference topics cover behavior mapping,\nrisk-based testing, test levels, workload modeling, oracles, fixtures, mocks,\nsuite health, static analysis, security testing, fuzzing, property-based\ntesting, mutation testing, performance testing, resilience testing, and\nregression selection.\n\n## Contributing\n\nKeep the public surface area small: one skill, `wio`, with command modes\n`scan`, `test`, `workload`, `review`, and `doctor`.\n\nDetailed testing guidance belongs in\n`plugins/wio/skills/wio/references/`, not duplicated inside cloud folders,\nsubagents, hooks, or extra skill trees. When adding a reference topic, add both\n`overview.md` and `tools.md`, then link it from\n`plugins/wio/skills/wio/references/index.md`.\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for contribution workflow and release\nexpectations.\n\n## License\n\nMIT. See [LICENSE](LICENSE).\n", "bytes": 8316, "sha": "09dbdc6a6d27f38054d0ac2de0a8ffb519ecac798b41d17e8f381cbfe0282000", "repo_slug": "workersio/skills", "fonte": "repo", "truncated": false, "api": "https://api.agentalog.com/api/listings/skl_workersio_skills_wio_3b7a3498/readme" }