Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
14 installs
Design & media
grill-skill
Try itBuild and harden a skill with evals — interview to design its eval tasks, then run, measure, and iterate. Use when the user wants to create or improve a skill's eval, or run the create → test → improve loop for a skill.
What it does
Build and harden a skill with evals — interview to design its eval tasks, then run, measure, and iterate. Use when the user wants to create or improve a skill's eval, or run the create → test → improve loop for a skill.
The skill document
Grill Skill
Interview the user to design a skill's eval, then loop run → measure → improve until it ships. Requires caliper (pipx install caliper-eval if missing). Commands, spec skeleton, and expect/assert guidance: REFERENCE.md.
Entry point
/grill-skill [path] — optional path to a SKILL.md.
- Path given — use it.
- No path — look for
SKILL.mdin the cwd; if found, confirm before proceeding, else ask where it is.
Phase 1 — Understand
Read the SKILL.md. Summarize what it does, when it triggers, and what a successful run looks like. Ask the user to confirm your reading. Wait for confirmation before continuing.
Phase 2 — Detect eval mode
Look for *.eval.yaml beside the SKILL.md (try .eval.yaml first).
- None → New eval. Found → Gap-fill.
Interview one question at a time and wait for each answer. Never invent the user's answers or write the spec before interviewing.
New eval — three tasks
Elicit three tasks, one question at a time:
- Happy path — the most common successful use. What did the agent do, and what would confirm it worked?
- Edge case — a tricky-but-valid input that might trip the raw agent.
- Adversarial — what the skill should refuse or avoid.
Turn each answer into a task: a realistic prompt, an observable expect, and an assert when the outcome is checkable (see REFERENCE.md). Show the proposed YAML and confirm before writing.
Write the spec beside SKILL.md, named .eval.yaml, with skill.path: ./SKILL.md and claude-code as the default backend for both skill and judge unless the SKILL.md targets another.
Gap-fill
Read the existing spec and report its tasks. Ask what behaviors are missing or under-tested before proposing or writing anything — even if the user only asked you to inspect it, report first, then ask. Sharpen each gap into a task, show it, and confirm before writing it in.
Phase 3 — First run
Validate the spec, then run at k=1 (commands in REFERENCE.md). Show the results. Fix any harness or config error (not a task failure) before asking the user what to do next.
Phase 4 — Iterate
Ask whether to iterate or finish.
- Iterate — after the user edits their
SKILL.md, re-run atk=3and show results. Loop back. - Done — suggest a
--baselinerun to prove the skill beats the raw agent, then remind the user to commitSKILL.mdand the.eval.yamltogether.
Related skills
Measure a skill's reliability — run it k times for a pass@k score, design or interpret its eval, or compare it against the base agent. Use when the user wants to run, design, or interpret a skill's eval, or write an .eval.yaml spec.
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
4 installs
Use when a technical writeup, blog post, war story, or "Show HN" is about to go to Hacker News, Lobsters, or any skeptical technical audience, or when the us...
1 installs
`skill-enhance` is an advanced skill for creating, improving, reviewing, and locally customizing other skills. It is designed for users who want a high-quality skill package rather than a minimal draft. It can help create new skills, strengthen existing ones, complete artifacts such as README and evals, improve trigger boundaries and workflows, and safely refine locally available skills after access and editability checks.
14 installs1 stars
Skill evolution system. Analyzes agent execution traces to generate Evolution Units (EUs — exploit/explore subtypes under the adaptive type), deploys them to...
3 installs1 stars