BC policy-and-managed-settings
Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting, configuration, or enterprise control—especially anything an organization or administrator may need to manage. Start here to decide whether it belongs in runtime managed settings, a typed SDK contract, VS Code configuration policy, extension policy, or a split implementation. Run on every new Copilot/agent/LLM control and ANY change that adds a `policy:` field.
The skill helps you decide where to put a new AI control: managed settings, SDK, VS Code policy, or extension. Promises to work on any change with a `policy:` field and when adding agents, models, or permissions.
Files are in place, no critical errors. Quality score is 80, but process score dropped to 52—documentation or examples likely incomplete. Targets administrators and extension developers who already know runtime from SDK. Steep learning curve for newcomers.
Install if you frequently add new controls to Copilot and tire of guessing where they belong. If you add controls once a year, you'll survive without it.
Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 24, 37, 40, 44, 48): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 809 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +4Structure: 2 headings, hard to scan
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 509: enough signal without eating the budget
- +3Step-by-step instructions: 17 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.