CtrlK
BlogDocsLog inGet started
Tessl Logo

best-practices

Best practices for Copilot Studio agents. Covers JIT glossary loading (customer acronyms, terminology), JIT user context provisioning (M365 profile, country, department), and the shared OnActivity initialization pattern. USE FOR: glossary, acronyms, user context, user profile, country-aware answers, JIT initialization, OnActivity provisioning, conversation-init, personalized knowledge. DO NOT USE FOR: general knowledge sources (use add-knowledge), topic creation (use new-topic).

Install with Tessl CLI

npx tessl i github:microsoft/skills-for-copilot-studio --skill best-practices
What are skills?

88

Quality

86%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SKILL.md
Review
Evals

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 follows best practices. It provides specific capabilities, comprehensive trigger terms via the USE FOR clause, and proactively prevents conflicts with the DO NOT USE FOR clause. The description is well-structured, uses third person voice, and gives Claude clear guidance on when to select this skill.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'JIT glossary loading (customer acronyms, terminology)', 'JIT user context provisioning (M365 profile, country, department)', and 'shared OnActivity initialization pattern'. These are concrete, actionable capabilities.

3 / 3

Completeness

Clearly answers both what (JIT glossary loading, user context provisioning, OnActivity pattern) AND when (explicit USE FOR and DO NOT USE FOR clauses with specific trigger scenarios). The DO NOT USE FOR clause adds valuable disambiguation.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'glossary', 'acronyms', 'user context', 'user profile', 'country-aware answers', 'personalized knowledge', 'conversation-init'. The USE FOR clause explicitly lists trigger terms.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with clear niche (Copilot Studio agents, JIT patterns). The DO NOT USE FOR clause explicitly prevents conflicts with 'add-knowledge' and 'new-topic' skills, showing awareness of potential overlaps.

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 routing skill that efficiently directs Claude to the appropriate detailed documentation. Its strength is in concise, clear navigation with good progressive disclosure. The main weakness is that actionability is entirely delegated to referenced files, and the combining patterns section could benefit from more explicit workflow steps.

Suggestions

Add a brief executable example or template snippet in the 'Combining patterns' section showing the merged OnActivity structure

Include explicit numbered steps for the merge workflow: 1) Copy template, 2) Add glossary logic, 3) Add user context logic, 4) Validate topic compiles

DimensionReasoningScore

Conciseness

The content is lean and efficient, serving as a routing document that assumes Claude's competence. No unnecessary explanations of what glossaries or M365 profiles are—just clear pointers to when each pattern applies.

3 / 3

Actionability

Provides clear decision criteria for when to read each file and mentions a template path, but lacks any concrete code/commands or executable examples in the main skill file itself. The actionable content is deferred entirely to referenced files.

2 / 3

Workflow Clarity

The 'Combining patterns' section hints at a workflow (merge into single topic) but lacks explicit steps or validation checkpoints. For a routing document this is acceptable, but the merge guidance could be more explicit about the sequence.

2 / 3

Progressive Disclosure

Excellent structure with clear overview and well-signaled one-level-deep references. Each section clearly indicates when to read the linked file, and content is appropriately split between this overview and detailed files.

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

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.