AD job-search-belgrade
Searches LinkedIn, Poslovi Infostud, and HelloWorld.rs for jobs matching your target roles. Scores each listing against your resume PDF (1-10 with justification) using your configured LLM. Results in chat, optional email digest, optional daily cron. No auto-applying. Cover letters on demand. Use when the user says: - "Run the job search" - "Find jobs for me" / "Search for jobs" - "Set up daily job search" / "Schedule the job search" - "Enable email for job results" - "Write a cover letter for [job title / company]" - "Generate a cover letter for [pasted job description]"
Searches LinkedIn, Poslovi Infostud, and HelloWorld.rs for jobs matching your target roles. Scores each listing against your resume PDF (1-10 with…
As a process D 47/100 · 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 · 0
✓ No critical or high findings
Files scanned: 10. 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 47/100
- 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
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (job-search-belgrade) differs from the folder (job-search-skill)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 33 steps
- 100Execution cost. Instruction body is 1378 tokens
- 100Progress reporting. Reports progress
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
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 577: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (6 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.