AC sanctifai
Human-in-the-loop skill for AI agents. Use when your agent needs humans to review, approve, or complete a task. Provides REST API and MCP (Model Context Protocol) integration with long-polling and webhooks. No server required — agents self-register and get responses back asynchronously.
Human-in-the-loop skill for AI agents.
As a process C 55/100 · Has gaps — weak spots: result and completion, consistency, execution cost
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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 24980 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 24980 tokens: crowds the task out of the window
- 40Consistency. Frontmatter name (sanctifai) differs from the folder (sanctifai-source)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 28 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 19 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
- +1No license
- +2Single-language instructions
- +3Description length 287: enough signal without eating the budget
- +4Structure: 79 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (90 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.