{"slug":"agent-tool-testing","title":"agent-tool-testing","summary":"Use this skill when you need to test AI agent tool-call contracts, authorization, failures, and side-effect boundaries; triggers include agent tool testing.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-24T14:54:53.176466Z","repo":{"url":"https://github.com/naodeng/awesome-qa-skills","stars":230,"forks":31,"license":null,"updatedAt":"2026-09-22T13:51:34Z"},"bodyHtml":"<hr>\n<h2>name: agent-tool-testing\ndescription: Use this skill when you need to test AI agent tool-call contracts, authorization, failures, and side-effect boundaries; triggers include agent tool testing.</h2>\n<h1>Agent Tool Testing</h1>\n<h2>When to Use</h2>\n<ul>\n<li>Use this skill when you need to verify an AI agent's tool selection, argument contracts, authorization, failure recovery, and side-effect boundaries.</li>\n<li>Use it to review an existing plan, result, or evidence set and produce actionable improvements.</li>\n<li>Use it when context is incomplete but a bounded first pass is still valuable.</li>\n</ul>\n<h2>Output Format Options</h2>\n<ul>\n<li>Default to Markdown for review, execution, and incremental refinement.</li>\n<li>When the user requests tables, CSV, JSON, or ticket fields, preserve risk, evidence, priority, and boundary information.</li>\n<li>For machine-consumed output, confirm the schema, enums, and required fields first.</li>\n</ul>\n<h2>How to Use</h2>\n<ol>\n<li>Read and follow <code>prompts/agent-tool-testing.md</code>, including its input contract, execution rules, minimum coverage, and output order.</li>\n<li>Add only context that changes the decision: scope, environment, version, constraints, evidence, and success criteria.</li>\n<li>Audit the input, then separate confirmed facts, working assumptions, and open questions.</li>\n<li>Rank by risk and evidence strength, and produce an artifact that can be executed or reviewed directly.</li>\n<li>If information is missing, deliver a bounded first pass and state which conclusions remain unsupported.</li>\n</ol>\n<h2>Reference Files</h2>\n<ul>\n<li>Always read <code>prompts/agent-tool-testing.md</code>; it is the complete execution specification for this skill.</li>\n<li>For evaluation or regression, read <code>evals/eval.yaml</code> and the relevant cases under <code>evals/cases/</code>.</li>\n<li>Load <code>references/</code>, <code>examples/</code>, <code>scripts/</code>, or <code>output-formats.md</code> only when those directories exist and the task needs them.</li>\n</ul>\n<h2>Core Constraints</h2>\n<ul>\n<li>default to mocks, dry runs, or isolated environments</li>\n<li>never execute real writes without authorization</li>\n<li>retry tests must detect duplicate side effects</li>\n<li>Never invent system behavior, fields, data, metrics, or root causes absent from the evidence.</li>\n<li>Link important conclusions to evidence; mark unsupported conclusions as hypotheses with a verification method.</li>\n<li>Explain priority using business impact, likelihood, or detectability.</li>\n</ul>\n<h2>Delivery Checklist</h2>\n<ul>\n<li><input disabled=\"disabled\" type=\"checkbox\"> Covered: tool-selection correctness, argument generation and validation, authorization, timeouts and retries, idempotency, side-effect isolation, result interpretation, audit evidence.</li>\n<li><input disabled=\"disabled\" type=\"checkbox\"> Separated facts, assumptions, gaps, and recommendations.</li>\n<li><input disabled=\"disabled\" type=\"checkbox\"> Gave high-risk items a priority, evidence basis, owner or next action.</li>\n<li><input disabled=\"disabled\" type=\"checkbox\"> Defined verifiable decision criteria instead of generic advice.</li>\n<li><input disabled=\"disabled\" type=\"checkbox\"> Performed no unauthorized production writes or destructive actions.</li>\n</ul>\n<h2>Common Pitfalls</h2>\n<ul>\n<li>Listing checks without preconditions, expected outcomes, or evidence.</li>\n<li>Marking everything high priority and avoiding tradeoffs.</li>\n<li>Substituting tool names or generic theory for domain reasoning.</li>\n<li>Refusing incomplete input, or pretending incomplete evidence supports certainty.</li>\n</ul>\n<h2>Best Practices</h2>\n<ul>\n<li>Start with paths most likely to cause business loss, safety issues, or release blockage.</li>\n<li>Reduce uncertainty through the smallest verifiable experiment and record reproduction conditions.</li>\n<li>Make the artifact executable and independently reviewable by another engineer.</li>\n</ul>\n","files":[{"path":"agents/openai.yaml","sizeBytes":312,"isText":true},{"path":"evals/cases/basic-success.yaml","sizeBytes":861,"isText":true},{"path":"evals/cases/edge-incomplete-input.yaml","sizeBytes":902,"isText":true},{"path":"evals/cases/edge-risk-priority.yaml","sizeBytes":861,"isText":true},{"path":"evals/eval.yaml","sizeBytes":557,"isText":true},{"path":"prompts/agent-tool-testing.md","sizeBytes":3497,"isText":true},{"path":"SKILL.md","sizeBytes":3362,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-24T14:56:41.601905Z","sha256":"611C0E5231B817825586E7C03F3ED558BBF84B9B7A7DD8F0421577B45F2546FD","sizeBytes":5915},"review":null,"source":{"repositoryUrl":"https://github.com/naodeng/awesome-qa-skills","path":"skills/en/testing-types/agent-tool-testing","license":null,"commit":"c44b8922085e01bafc804d1ffa3f21d4cec1d1c5","subtreeSha":"0A422345BD46E3F6179FF97721E01EABD419CD4AA0982A7EE84F83B456B375D0","lastSyncedAt":"2026-09-24T14:54:50.849933Z"},"reviewedAt":"2026-09-24T15:03:38.702681Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/naodeng/awesome-qa-skills/tree/main/skills/en/testing-types/agent-tool-testing"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install naodeng-awesome-qa-skills@llmmart"},{"target":"git","command":"git clone https://github.com/naodeng/awesome-qa-skills.git"}]}