AC autoskill
Intelligent skill router. Analyzes the current problem statement and context, scores all available skills for applicability, and recommends the most relevant ones in priority order. **No skill is ever invoked without your explicit approval.** Use when you want Claude to automatically identify and recommend the right skills without manually choosing them. Great for complex tasks where the right set of skills is non-obvious. Invocation: /autoskill [problem description] /autoskill (uses current conversation context if no args given) Examples: /autoskill fix the login bug that crashes on empty password /autoskill add unit tests for the payment module /autoskill review my PR before I merge /autoskill (running with no args analyzes the current conversation)
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Glob Grep AskUserQuestion Skill
-
low Risky intent
intent-offensive-securitySKILL.md:148Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `security` | security, auth, vulnerability, owasp, bounty, pentest |
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "preamble-tier" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 18 mutating operations with no state check
- 70Failures and branches. 6 branches
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3723 tokens
- 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
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 776: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.