Skip to content
cccskills
FreePublished on GitHub

grill-with-docs

Stress-test a Yuzu plan against the repo's domain language, code, CONTEXT.md, and ADRs while updating docs as decisions crystallize. Use when the user says `/grill-with-docs`, asks to grill a design with docs, wants decision interrogation, or needs ADR-adjacent planning.

The English summary is being prepared. Showing the original description.

DevNullLtd/Yuzu
See how to install

Files included (1)

  • SKILL.md1.7 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Grill With Docs

Interrogate one decision at a time. Ask a question, provide your recommended answer, and wait for feedback. If the answer can be discovered from the codebase or docs, inspect them instead of asking.

Inputs

Read lazily:

  • CONTEXT.md for glossary and domain boundaries.
  • docs/adr/ for existing architectural decisions relevant to the topic.
  • Code and docs that implement or describe the plan's domain.

Create files lazily only when there is something real to record.

During The Session

  • Challenge terms that conflict with CONTEXT.md.
  • Replace vague terms with canonical Yuzu terms.
  • Use concrete scenarios that stress boundary cases, permissions, failure modes, and operator-visible behavior.
  • Cross-check claims against code when feasible.
  • Update CONTEXT.md inline when a domain term is resolved.

CONTEXT.md Format

Keep terms domain-level, not implementation trivia:

## Term

Definition in Yuzu language.

- Related concepts: ...
- Avoid saying: ...

ADR Rule

Offer an ADR only when all are true:

  • hard to reverse
  • surprising without context
  • a real trade-off among credible alternatives

ADRs live in docs/adr/ and are numbered 0001-short-title.md, 0002-short-title.md, etc. Use this shape:

# ADR-NNNN: Title

## Status

Accepted

## Context

## Decision

## Consequences

There is no separate /adr workflow initially; this skill is the ADR-adjacent workflow.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

adversarial-review

Free

Run an adversarial two-phase code review of a change with TWO independent reviewers — Claude and Codex — who review alone, then cross-examine each other's findings, then Claude synthesizes a single weighted verdict. Use when the user says "/adversarial-review", "adversarial review", "review this with Codex", "get Codex to review", "two-reviewer review", "cross-examine this PR", or wants a second independent model to grade a change before merge.

The English summary is being prepared. Showing the original description.

DevNullLtd/Yuzu19Updated Oct 20, 2026

auth-and-authz

Free

Authentication & Authorisation control plane for Yuzu — the canonical entry point for any work on RBAC, OIDC SSO, SAML, SCIM, MFA/TOTP, AD/Entra integration, API tokens, session lifecycle, enrollment, and the audit/evidence chain. Use when the user says "/auth-and-authz", "/auth", "/iam", asks to plan or implement an enterprise A&A feature, asks "what's our auth gap to enterprise readiness", asks to audit current auth state against SOC 2 CC6.x / Workstream B, or starts work that touches `auth_*`, `rbac_*`, `oidc_*`, `api_token_*`, `enrollment_*`, or `cert_store.*`. The skill bundles current-state inventory, required-features inventory, gap matrix, the canonical workflow for adding a new A&A feature, and the load order for the routed reference docs.

The English summary is being prepared. Showing the original description.

DevNullLtd/Yuzu19Updated Oct 20, 2026

ci-cache

Free

Canonical patterns for caching in Yuzu CI workflows. Two snippets — one for ephemeral GHA-hosted runners (split actions/cache/restore + actions/cache/save, never `save-always: true`) and one for self-hosted runners (local filesystem cache under `runner.tool_cache`, no GHA cache round-trip). Use when adding a new vcpkg/ccache/dependency cache step to any workflow under `.github/workflows/`, or when reviewing a PR that touches `actions/cache@`.

The English summary is being prepared. Showing the original description.

DevNullLtd/Yuzu19Updated Oct 20, 2026

cpp-expert

Free

Review Yuzu C++ source changes for C++23 correctness, idiomatic standard-library use, ABI boundaries, threading primitives, and cross-compiler portability across GCC, Clang, MSVC, and Apple Clang. Use for any governance Gate 3 review when `.cpp`, `.hpp`, or `.h` files change.

The English summary is being prepared. Showing the original description.

DevNullLtd/Yuzu19Updated Oct 20, 2026

cpp-safety

Free

Review Yuzu C++ source changes for resource ownership, RAII, borrowed lifetimes, C ABI contexts, casts, process/syscall boundaries, callbacks, threads, and sanitizer coverage. Use for any governance Gate 3 review when C++ files change, paired with cpp-expert.

The English summary is being prepared. Showing the original description.

DevNullLtd/Yuzu19Updated Oct 20, 2026

dev-team

Free

Run the current session as a senior developer (Opus) leading a configurable junior fleet. Decomposes requests into scoped tasks, dispatches junior-developer subagents in parallel, optionally runs an architect plan-review gate before dispatch, autonomously resolves escalations, optionally dispatches a doc-writer second wave after juniors complete, then integrates and gates with /test + /governance. Use when the user says "/dev-team", "run the dev team", "delegate this to the juniors", "act as the senior dev", or wants a task built by a senior-led fleet.

The English summary is being prepared. Showing the original description.

DevNullLtd/Yuzu19Updated Oct 20, 2026

See all skills by DevNullLtd

Report a problem with this skill