AB cyber-interviewer
Review a candidate's local PDF resume and GitHub repositories, inspect Python and C++ code paths for strengths and weaknesses, search recent interview experience writeups for a target role or company, and run a tough technical mock interview grounded in local files plus live web context. The interview should cross-examine exact code paths, weak points, and tradeoffs, and should add algorithm pressure when the target role is likely to include coding rounds. Use when the user wants resume review, project deep-dives, interview prep, or a company-specific mock interview. Prefer giving a GitHub username over manually listing repos when the host can discover public repositories automatically.
As a process B 79/100 · Nearly there — no weak spots found
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: 6. 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 79/100
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4059 tokens
- 100Steps. 264 steps
- 100Failures and branches. 15 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 23 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (12 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 695: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 264 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.