Research and strategy
Agent readiness
Assess whether an agent can discover, understand and complete a defined task, with evidence for each stage.
Open-source skill · format validated
When this is useful
Assess how well an AI agent can discover, understand, and complete a defined developer-tool or data-product task through public docs, APIs, SDKs, CLIs, MCP tools, or Agent Skills. Use for agent-readiness audits and reports; do not equate machine-readable files with successful execution.
What to bring
Named product and task, public entry points, available agent interfaces, allowed credentials and sandbox, and whether this is a public-only or hands-on assessment.
What you can work toward
A task-scoped evidence matrix, a clearly bounded readiness finding, reproducible test notes if performed, and a ranked remediation list.
Developer-tool version
Assess a defined engineering task through available docs/API/SDK/CLI/MCP/skills paths. Separate discoverability, documented setup, authorized execution, result verification, and recovery; no particular interface file is sufficient or mandatory.
Data-product version
Assess a defined data task through documented interfaces, scoped access, schema discovery, query/workload cost, correctness, freshness, and partial-failure recovery. Public-only evidence cannot prove authenticated execution or production data readiness.
How to use it
Choose the version for your product type and follow its repository installation instructions. Keep the skill folder, references and any assets together. Each skill works on its own; reuse a shared brief when helpful rather than repeating a full intake.
The source follows the open Agent Skills format and is MIT licensed. Live research and execution depend on the tools and permissions available in your host. Preparing a plan or draft does not itself authorize publishing, messaging, spending or production changes.
A starting prompt
Use the agent readiness skill for our developer tool or data product. Our task is [specific task], our supported environment is [environment], and the decision is [decision]. Use these facts and sources: [evidence]. Produce the requested artifact, label unknowns, and do not invent results or perform external actions beyond my authorization.
How to judge the result
A visible MCP endpoint or llms.txt file does not prove execution. A missing one does not prove failure. Do not bypass authentication, incur unapproved charges, or expose private audience results.
Check that the product-specific version changes the recommendation, the requested deliverable is complete, and proposed tests are distinguished from observed results. Format validation does not establish how a model will perform on your product.
From input to reviewed output
Put it to work
- Choose the collection for your product type and install the relevant skill with its bundled references and assets.
- Supply the task, supported behavior, existing evidence and constraints that affect the decision. Reuse context already available.
- Ask for the concrete deliverable, distinguishing facts, hypotheses, unknowns and any untested instructions.
- Check the product-specific acceptance criteria, source claims and next steps before using or publishing the output.
Limits and tradeoffs
A visible MCP endpoint or llms.txt file does not prove execution. A missing one does not prove failure. Do not bypass authentication, incur unapproved charges, or expose private audience results. No fresh-host model performance is claimed; verify output against your product, evidence and authorized environment.