CA setup-auth
Use when the user asks to "set up authentication", "add login", "add logout", "add sign in", "enable auth", "add role-based access", "add authorization", "protect routes", "configure identity provider", "configure Entra ID", "configure Entra External ID", "configure OpenID Connect", "add OIDC", "set up SAML", "set up WS-Federation", "set up local login", "add Facebook login", "add Google sign in", "add Microsoft Account", or otherwise wants to set up authentication (login/logout) and role-based authorization for their Power Pages SPA site using any supported identity provider. Also sets up the IdP app registration for OIDC providers (Okta, Auth0, Entra External ID, and other OIDC) -- reads the provider's docs first, then either guides the user through the provider's console or, when the provider supports it, configures it for the user -- and wires the client ID, authority, and claims mapping into Power Pages.
Use when the user asks to "set up authentication", "add login", "add logout", "add sign in", "enable auth", "add role-based access", "add authorization"…
As a process A 85/100 · Runs to the end — weak spots: execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Grep Glob AskUserQuestion Task TaskCreate TaskUpdate TaskList Skill mcp__plugin_power-pages_microsoft-learn__microsoft_docs_search mcp__plugin_power-pages_microsoft
-
low Secrets in code
secret-high-entropy-tokenreferences/authentication-reference.md:857High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)* identifier (a long opaque string like `vs25…EZQ`) — showing
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:3023High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **User profile display**: After login, the auth service's `getUserDisplayName()` falls back through `firstName + lastName` → `firstName` → `lastName` → `email` → `userName` → `'User'`. **Email beats
quoted
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 57029 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 138, 158, 214, 701, 711, 870): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 85/100
- 10Execution cost. Instruction body is 57029 tokens: crowds the task out of the window
- 60Steps. 424 steps, 26 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. Tools declared in frontmatter
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 54 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (16 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 922: 120–800 characters recommended
- -2localhost URLs: will not work for another user
- -246 emoji in the instructions: noise for the model
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 19 example trigger phrases
- +4Structure: 86 headings
- +3Step-by-step instructions: 424 items
- +3Output format is stated explicitly
- +4Has examples (59 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.