best-practices
Best practices for Copilot Studio agents. Covers JIT glossary loading (customer acronyms, terminology), JIT user context provisioning (M365 profile, country, department), the shared OnActivity initialization pattern, dynamic topic redirects with Switch expressions, and preventing child agents from responding directly to users. USE FOR: glossary, acronyms, user context, user profile, country-aware answers, JIT initialization, OnActivity provisioning, conversation-init, personalized knowledge, dynamic redirect, Switch, BeginDialog, if/then/else replacement, child agent responses, completion setting, SendMessageTool, output variables, connected agents. DO NOT USE FOR: general knowledge sources (use add-knowledge), topic creation (use new-topic).
88
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that covers all evaluation dimensions strongly. It provides specific concrete capabilities, comprehensive trigger terms via an explicit USE FOR list, clear when-to-use guidance, and even includes DO NOT USE FOR anti-triggers to prevent conflicts with related skills. The description is well-structured and uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: JIT glossary loading, JIT user context provisioning, shared OnActivity initialization pattern, dynamic topic redirects with Switch expressions, and preventing child agents from responding directly to users. These are highly specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (best practices for Copilot Studio agents covering specific patterns like JIT glossary loading, OnActivity initialization, dynamic redirects) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with comprehensive trigger terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms via the explicit 'USE FOR' list including terms like 'glossary', 'acronyms', 'user context', 'user profile', 'country-aware answers', 'dynamic redirect', 'Switch', 'child agent responses', etc. Also includes 'DO NOT USE FOR' anti-triggers which further improves routing quality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Copilot Studio agent patterns) and explicit boundary-setting via 'DO NOT USE FOR' clauses that redirect to other skills (add-knowledge, new-topic). The specific technical patterns like OnActivity, Switch expressions, and JIT provisioning are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured index/routing skill that efficiently directs Claude to the right detailed file based on the user's need. Its strengths are excellent progressive disclosure and conciseness. Its main weakness is that the body itself contains no executable guidance — all actionability is deferred to linked files — and the combining patterns section could benefit from a concrete example or clearer workflow steps.
Suggestions
Add a brief concrete example in the 'Combining patterns' section showing the key merge points (e.g., a snippet of the combined conversation-init topic YAML structure)
Consider adding a short numbered workflow for when multiple patterns need to be combined (e.g., 1. Identify which patterns apply, 2. Use the conversation-init template, 3. Merge the relevant initialization blocks)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. Descriptions are brief but informative, clearly stating what each pattern does and when to read it. No unnecessary explanations of concepts Claude already knows. | 3 / 3 |
Actionability | The skill itself is an index/router to detailed files, which is appropriate, but it contains no executable code, commands, or concrete examples in the body. The actionable content is deferred entirely to linked files. The 'Combining patterns' section mentions a template path but doesn't show how to use it. | 2 / 3 |
Workflow Clarity | The 'Read this best-practice when' sections provide clear routing logic, and the combining patterns note mentions merging into a single topic. However, there's no explicit sequencing for how to combine patterns, no validation steps, and no guidance on order of operations when multiple patterns apply. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. Clear overview with well-signaled one-level-deep references to specific files. Each section has a concise description and explicit 'when to read' triggers. The instruction to only read the relevant file is a smart token-saving directive. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- microsoft/skills-for-copilot-studio
- Commit
5c1cc83
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.