CD lokaler-companion
Baut einen "Companion" — eine lokal laufende Beobachtungs-Anwendung: kleiner Server auf 127.0.0.1, Doppelklick-Starter, installierbare PWA, optionale Browser-Erweiterung, Meldung beim Zustandswechsel, Dauerbetrieb im Container. Nutze diesen Skill, sobald jemand etwas dauerhaft im Auge behalten und benachrichtigt werden will — Livestreams, Kanäle, Feeds, Preise, Build-Zustände, Serververfügbarkeit, Ordner, Warteschlangen. Auch wenn die Anfrage nur nach einem Teil klingt: "sag mir Bescheid wenn X online geht", "kleines Tool das im Hintergrund läuft", "Statusseite für Y", "als App installierbar", "soll dauerhaft laufen", "auch nach Neustart", "als Docker-Container". Besonders wichtig bei einer einzelnen HTML-Datei, die fremde Daten abruft: ob das trägt, hängt an einer CORS-Freigabe, die man vorher prüfen muss — sonst bleibt die Datei beim Nutzer leer.
Baut einen "Companion" — eine lokal laufende Beobachtungs-Anwendung: kleiner Server auf 127.0.0.1, Doppelklick-Starter, installierbare PWA, optionale…
As a process D 48/100 · Unfinished process — 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 8
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-execpolicy-bypassreferences/starter.md:82Runs PowerShell with execution policy bypassedpowershell -NoProfile -ExecutionPolicy Bypass -File "%~dp0s…ps1" %*
-
medium Dangerous commands
cmd-persistencereferences/starter.md:129Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- **macOS**: `launchd`-Datei unter `~/Library/LaunchAgents/`
quoted -
medium Dangerous commands
cmd-execpolicy-bypassscripts/starter/Beenden.cmd:3Runs PowerShell with execution policy bypassedpowershell -NoProfile -ExecutionPolicy Bypass -File "%~dp0s…ps1" -Stop
-
medium Dangerous commands
cmd-execpolicy-bypassscripts/starter/Fehlersuche.cmd:4Runs PowerShell with execution policy bypassedpowershell -NoProfile -ExecutionPolicy Bypass -File "%~dp0s…ps1" -Console
-
medium Dangerous commands
cmd-execpolicy-bypassscripts/starter/Start.cmd:2Runs PowerShell with execution policy bypassedrem Doppelklick-Einstieg. -ExecutionPolicy Bypass gilt nur fuer diesen einen
-
medium Dangerous commands
cmd-execpolicy-bypassscripts/starter/Start.cmd:5Runs PowerShell with execution policy bypassedpowershell -NoProfile -ExecutionPolicy Bypass -File "%~dp0s…ps1" %*
-
low Dangerous commands
cmd-background-processreferences/docker.md:122Starts a background / autostarted process (quoted — discussed, not commanded)- **Linux**: `sudo systemctl enable docker` — auf den meisten Systemen ohnehin
quoted -
low Dangerous commands
cmd-execpolicy-bypassreferences/starter.md:85Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)`-ExecutionPolicy Bypass` gilt nur für diesen einen Aufruf und ändert nichts
quoted
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 48/100
- 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
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 40 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3566 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 tags): a typed call is more reliable
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 860: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.