skills/validate/SKILL.md
Validate Copilot Studio agent YAML files using the LSP binary's full diagnostics (YAML structure, Power Fx, schema, cross-file references). Use when the user asks to check, validate, or verify YAML files.
npx skillsauth add microsoft/skills-for-copilot-studio skills/validateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Validate Copilot Studio agent YAML files using the LanguageServerHost binary's full diagnostics — the same validation engine used by the VS Code Copilot Studio extension.
Locate the agent workspace. Find the directory containing .mcs/conn.json. If a specific file was requested, use the workspace that contains it.
Run LSP-based validation:
node ${CLAUDE_SKILL_DIR}/../../scripts/manage-agent.bundle.js validate \
--workspace "<path-to-agent-folder>" \
--tenant-id "<tenantId>" \
--environment-id "<envId>" \
--environment-url "<envUrl>" \
--agent-mgmt-url "<mgmtUrl>"
This validates all .mcs.yml files in the workspace using the LSP binary's full diagnostics: YAML structure, Power Fx expressions, schema validation, cross-file references, and environment-specific checks.
Connection details come from .mcs/conn.json — read it to get tenant-id, environment-id, environment-url, and agent-mgmt-url.
Parse the JSON output:
valid: true → all files pass (may still have warnings)valid: false + summary.errors > 0 → report errors as FAIL itemssummary.warnings > 0 → report as WARN itemsIf the user asked about a specific file, filter the output to show only that file's diagnostics.
For additional context on specific errors, use schema lookup:
node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js resolve <kind>
Report findings:
Validation Results for: <agent-name>
[PASS] <filename> — no issues
[FAIL] <filename> — <error message> (line X)
[WARN] <filename> — <warning message> (line X)
Summary: X files checked, Y errors, Z warnings
development
Authenticate for Copilot Studio evaluation API and SDK chat. Caches a token that is shared across run-eval and chat-sdk skills. Run this before any eval or SDK chat workflow. Requires an App Registration with MakerOperations and Copilots.Invoke permissions.
development
Run a batch test suite via the Copilot Studio Kit (Dataverse API). Uses the Power CAT Copilot Studio Kit to execute test cases against a published agent and produces pass/fail results with latencies. Requires the Kit installed in the environment, an App Registration with Dataverse permissions, and a published agent.
development
Run evaluations against a Copilot Studio agent via the Power Platform Evaluation API. Works on DRAFT agents — no publish step required. Lists test sets, starts a run, polls until complete, fetches results, and proposes YAML fixes for failures. Use when the user wants to test agent changes without publishing.
development
Index of repeatable implementation patterns for Copilot Studio agents. When a request may need a best-practice architecture or reusable pattern for building an agent capability, retrieve this index before deciding what detailed guidance is relevant. Do not decide from this frontmatter alone; use the index summaries, then open only the specific pattern file if needed. Do not use for general knowledge sources or topic creation.