AB geofeed-tuner
Use this skill whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a self-published IP geolocation feed in CSV format. Intended user audience is a network operator, ISP, mobile carrier, cloud provider, hosting company, IXP, or satellite provider asking about IP geolocation accuracy, or geofeed authoring best practices. Helps create, refine, and improve CSV-format IP geolocation feeds with opinionated recommendations beyond RFC 8805 compliance. Do NOT use for private or internal IP address management — applies only to publicly routable IP addresses.
Use this skill whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a self-published…
As a process B 78/100 · Nearly there — weak spots: 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitySKILL.md:538Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Generate a new **script** _only_ for payload generation (read the dataset and write one or more payload JSON files; do not call MCP from this script).
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 11957 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 102, 113, 260, 328, 389): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 78/100
- 40Execution cost. Instruction body is 11957 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (read, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 170 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 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
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
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 629: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 170 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.