AD planesnitch
Self-hosted aircraft monitor — watches one or more named locations for interesting aircraft (military/gov/police via plane-alert-db CSVs, emergency squawks 7500/7600/7700, custom ICAO hex/type lists, low-flyers by altitude, or literally everything) using free online ADS-B APIs (adsb.lol, adsb.fi, airplanes.live, adsb.one) or your own ultrafeeder — no SDR, no antenna, no hardware. Fires alerts to Telegram (with doc8643 aircraft-type photos) and/or webhooks (JSON array + base64 image), per-alert cooldowns, config-file driven (config.yaml), runs in Docker. Use when the user wants to monitor/alert on aircraft near a location, get pinged when a military/government/police plane flies overhead, watch for emergency squawks, or build their own plane-spotting radar without buying hardware.
Self-hosted aircraft monitor — watches one or more named locations for interesting aircraft (military/gov/police via plane-alert-db CSVs, emergency squawks…
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
exfil-webhook-urlreferences/setup.md:296Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)2. **Personal alerts:** send your bot a message first, then check `https://api.telegram.org/bot<TOKEN>/getUpdates` — your `chat_id` is in there.
placeholder
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2003 tokens
- 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
- +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 790: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.