AC records-retention-schedule-drafter
Use this skill when a RIM lead, IG officer, compliance officer, or legal-ops professional needs to draft an ARMA GARP-aligned records retention schedule. Covers multi-jurisdictional regulatory citations, privacy-law minimization overlays, and format-specific disposition. Produces a DRAFT schedule for governance-committee review — not legal advice.
As a process C 60/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitySKILL.md:121Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **Backup and DR copies** | Backup retention vs production retention; the "delete from production / overwrite in backup" gap; immutable / WORM backup considerations; ransomware-recovery snapshots |
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6618 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 18 mutating operations with no state check
- 60Steps. 32 steps, 4 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 6618 tokens
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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)
- +1No license
- +2Single-language instructions
- +3Description length 349: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.