AD jobclaw
AI-powered automated job search skill. Searches LinkedIn and Indeed daily, scores jobs against the user's profile, and saves results to a local CSV. Use when: - User says "run job search", "find jobs", "search for jobs", "start daily job search" - User types "/newjob URL" to analyse a specific job posting - User asks to set up automated daily job searching - User asks to show job stats, top matches, or update a job status - User asks to configure or set up job search preferences - User asks for "job tracker", "JobClaw", or "job search automation" First-time setup: guide the user through conversational onboarding (see Conversational Setup below). After setup: search.py handles all searching; run_daily.sh for the full automated pipeline. Install via ClawHub: clawhub install job-claw
As a process D 49/100 · 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 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.
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
-
medium Exfiltration
exfil-webhook-urlscripts/notify.py:151Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)url = f"https://api.telegram.org/bot{bot_token}/sendMessage"quoted
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
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
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (jobclaw) differs from the folder (job-claw)
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 27 steps
- 100Execution cost. Instruction body is 1796 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- -32 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 793: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.