DC dotfile
Synchronization management with external tools. agents - Windows+WSL ~/.agents share + ~/.claude/plugins split layout [agents.md], chezmoi - dotfile template management [chezmoi.md], knowledge - session knowledge → Serena memory [knowledge.md], mcp - MCP server synchronization [mcp.md], syncthing - chezmoi Syncthing sync and diagnostics [syncthing.md]. Use when "knowledge sync", "chezmoi add", "dotfile management", "syncthing", "MCP server add", "MCP sync", "external sync", "(?d)", ".stignore", "ignored files", "stignore settings", "sync incomplete", "sync status", "DB reset", "stale cache", "syncthing diagnostics", "index reset", "rescan", "encryption consistency", "Failed to verify encryption", "receive-encrypted mismatch", "garbage encryptionPassword", "Antigravity Syncthing", "Gemini Syncthing re-register", "Windows WSL agents layout", "plugins split", "marketplace EACCES". For ClawHub-related tasks → delegate to /clawhub skill.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 9
-
high Exfiltration
exfil-send-secrets-to-urlsyncthing.md:193Instruction to send secrets/history to an external endpoint (describes API authentication (bearer / header / HTTPS))curl -s -X POST -H "X-API-Key: $API_KEY" "http://loca…384/rest/db/scan?folder=<FOLDER_ID>"
API auth -
high Dangerous commands
cmd-persistencesyncthing.md:300Persistence mechanism (cron / launchd / scheduled task / autorun registry)Register-ScheduledTask `
Medium and low: 7
-
medium Exfiltration
net-credential-usesyncthing.md:14Credential used in a network call (verify the destination is the intended service)curl -X POST -H "X-API-Key: $API_KEY" \
-
medium Exfiltration
net-credential-usesyncthing.md:157Credential used in a network call (verify the destination is the intended service)curl -s -H "X-API-Key: $API_KEY" "http://loca…384/rest/db/status?folder=<FOLDER_ID>"
-
medium Exfiltration
net-credential-usesyncthing.md:173Credential used in a network call (verify the destination is the intended service)curl -s -H "X-API-Key: $API_KEY" "http://loca…384/rest/db/need?folder=<FOLDER_ID>"
-
medium Exfiltration
net-credential-usesyncthing.md:176Credential used in a network call (verify the destination is the intended service)curl -s -H "X-API-Key: $API_KEY" "http://loca…384/rest/db/completion?folder=<FOLDER_ID>&device=<DEVICE_ID>"
-
medium Exfiltration
net-credential-usesyncthing.md:183Credential used in a network call (verify the destination is the intended service)curl -s -H "X-API-Key: $API_KEY" http://loca…384/rest/system/connections
-
medium Dangerous commands
cmd-persistencesyncthing.md:255Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)**Recommended approach**: Task Scheduler at user logon + VBS launcher for hidden execution. No password storage required. Run admin steps via `gsudo` (a Windows `sudo`-equivalent — installs via `winge
quoted -
medium Dangerous commands
cmd-execpolicy-bypasssyncthing.md:312Runs PowerShell with execution policy bypassedgsudo powershell -NoProfile -ExecutionPolicy Bypass -File "$env:USERPROFILE\.local\share\sync…ps1"
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "depends-on"
Process rating: all ten parameters 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 592 tokens
- 100Running it twice. Mutating operations check current state
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 946: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -32 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 26 example trigger phrases
- +4Structure: 8 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (5 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.