Borrowing it
Nothing to install: this file belongs to DaveVoyles/resume-builder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DaveVoyles/resume-builder/main/.claude/skills/grill/SKILL.mdgit clone --depth 1 https://github.com/DaveVoyles/resume-builderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/davevoyles/resume-builder/grill)<a href="https://agentmods.dev/skills/davevoyles/resume-builder/grill"><img src="https://agentmods.dev/badge/skills/davevoyles/resume-builder/grill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/davevoyles/resume-builder/grill"><img src="https://agentmods.dev/badge/skills/davevoyles/resume-builder/grill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00468 |
| Opus 5.5 | $0.00000 | $0.00187 |
| Sonnet 5.5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
grill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill: Intake interview skill
Grill is an intake interview that captures work history, target roles, location preferences, compensation, and constraints into the candidate workspace.
What it does
The person drops source files in my-documents. Copy them into candidate/inputs/resumes or candidate/inputs/notes before ingest. Always name those real paths. Never say "the resumes folder."
The grill guides an agent through a structured conversation with the candidate, one question at a time. Answers are written to:
candidate/profile.json— Work history and candidate factscandidate/preferences.json— Target roles, location, salary, deal breakerscandidate/evidence.jsonl— Supporting evidence for claims
The agent makes the semantic decisions (asking follow-up questions, rephrasing, linking evidence); the CLI validates the output.
Usage
Use this skill when you're ready to conduct an intake interview with a candidate. The playbook is the source of truth:
docs/playbooks/grill.md
Paste the playbook into your terminal agent (Claude, ChatGPT, Copilot CLI, etc.) and follow along.
Playbook sections
The grill walks through:
- Work history — Roles, dates, locations, and impact
- Target role — Job titles, seniority, industries
- Location and work mode — Preferred regions and remote/hybrid/on-site
- Salary and compensation — Base, total, and ranges
- Constraints and deal breakers — Non-negotiables
After intake
After the grill completes:
-
Validate the workspace:
npm run workspace:validate -- --workspace candidate -
Review the captured facts with the candidate.
-
Proceed to the next step: ingest resumes, find similar roles, or tailor resumes.
Schema reference
See Candidate workspace schemas for the full shape of profile.json, preferences.json, and evidence.jsonl.
Related playbooks
tailor.md— Build a resume for a specific job postingfind-roles.md— Search for and vet candidate roles (coming soon)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +2 lines 893ee51dd7b2
- 2mo ago First seen · 56 lines · 0 tokens per session scan A 3351567406e3
grill is a skill published in the GitHub repository DaveVoyles/resume-builder (11 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
grill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grillDaveVoyles/resume-builder | Skill | 11 | 5d ago | MIT | A | 0 | Claude Code |
| cv-resume-builderorganvm-iv-taxis/a-i--skills | Skill | 17 | 2mo ago | Apache-2.0 | A | 62 | Claude Code |
| tracklytrackly-app/trackly-cli | Skill | 3 | today | MIT | A | 44 | Codex |
| job-navigation-skillxinyu0115/job-navigation-skill | Skill | 10 | 2mo ago | MIT | A | 138 | Codex |
| cv-creatorcuriositech/windags-skills | Skill | 18 | yesterday | none | A | 92 | Claude Code |
| trackly-applytrackly-app/trackly-cli | Skill | 3 | today | MIT | C | 59 | Codex |
| DevOps Engineer Resume OptimizerPramodDutta/qaskills | Skill | 245 | 4d ago | MIT | A | 41 | Claude Code, Codex |