agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when structuring a Cargo workspace or building a Rust CI pipeline — fmt, clippy, cargo-deny/audit, nextest, coverage, MSRV. Not for writing the tests themselves (rust-testing-quality).
$ npx -y skills add fusengine/agents --skill rust-tooling-cicd --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/rust-tooling-cicdContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when structuring a Cargo workspace or building a Rust CI pipeline — fmt, clippy, cargo-deny/audit, nextest, coverage, MSRV. Not for writing the tests themselves (rust-testing-quality).
name: rust-tooling-cicd description: Use when structuring a Cargo workspace or building a Rust CI pipeline — fmt, clippy, cargo-deny/audit, nextest, coverage, MSRV. Not for writing the tests themselves (rust-testing-quality). versions: cargo: "1.9x (edition 2024)" cargo-deny: "0.16" cargo-nextest: "0.9" user-invocable: false references: references/workspaces-features.md, references/ci-gate.md, references/templates/ci-workflow.md, references/templates/deny-toml.md related-skills: rust-testing-quality, solid-rust
<objective> This skill covers structuring Cargo workspaces (member layout, workspace.dependencies inheritance, feature design, MSRV) and building the canonical Rust CI gate: fmt → clippy (-D warnings) → cargo deny → cargo audit → nextest → cargo test --doc → coverage, in that fixed order so cheap checks fail fast.
It also covers supply-chain policy as code — committing deny.toml, centralizing dependency versions in [workspace.dependencies] rather than pinning per member — and auxiliary tooling like cargo hack (feature-powerset checks) and cargo machete (unused-dependency pruning).
Out of scope: writing the tests themselves (unit/integration/proptest/criterion) belongs to rust-testing-quality; non-Rust CI pipelines are not covered. </objective>
Before ANY tooling/CI work, spawn 3 agents in parallel, one `Agent` call each with a `name`:
1. **fuse-ai-pilot:explore-codebase** - Inspect existing `Cargo.toml`, workspace layout, `.github/workflows` 2. **fuse-ai-pilot:research-expert** - Verify current cargo / cargo-deny / nextest docs via Context7/Exa 3. **mcp__context7__query-docs** - Check workspace-inheritance and feature-unification specifics
After implementation, run **fuse-ai-pilot:sniper** for validation.
---
| Layer | Tool(s) | Purpose | |-------|---------|---------| | **Layout** | Cargo workspaces | One `Cargo.lock`, one `target/`, shared metadata | | **Config** | features, `workspace.dependencies` | Optional functionality, single source of versions | | **Format/lint** | `cargo fmt`, `cargo clippy` | Style + correctness lints, warnings as errors | | **Supply chain** | `cargo deny`, `cargo audit` | Licenses, bans, duplicate/yanked/vulnerable crates | | **Test** | `cargo nextest`, `cargo test --doc` | Fast parallel run + doc-tests | | **Coverage/MSRV** | `cargo llvm-cov`, `cargo hack` | Line coverage, minimum-supported-Rust matrix |
---
1. **Gate order is fixed** - fmt → clippy → deny → audit → nextest → `test --doc` → coverage. Cheap, fast-failing checks run first. 2. **`-D warnings` on clippy in CI** - `cargo clippy --all-targets --all-features -- -D warnings`. A warning must fail the build. 3. **Commit `deny.toml`** - supply-chain policy is code; it must be reviewed and versioned. 4. **Centralize versions in `workspace.dependencies`** - members inherit with `dep.workspace = true`; never pin the same crate twice. 5. **`cargo test --doc` is a separate step** - nextest never runs doc-tests (see rust-testing-quality).
---
my-workspace/ ├── Cargo.toml # [workspace] members + workspace.dependencies + lints ├── Cargo.lock # single lockfile, committed ├── deny.toml # supply-chain policy, committed ├── crates/ │ ├── core/Cargo.toml # inherits version.workspace = true │ └── cli/Cargo.toml └── .github/workflows/ci.yml
→ See [ci-workflow.md](references/templates/ci-workflow.md) and [deny-toml.md](references/templates/deny-toml.md)
---
| Topic | Reference | When to Consult | |-------|-----------|-----------------| | **Workspaces & features** | [workspaces-features.md](references/workspaces-features.md) | Structuring members, inheriting deps, feature design, MSRV | | **CI gate** | [ci-gate.md](references/ci-gate.md) | Ordering checks, cargo-deny/audit, coverage |
| Template | When to Use | |----------|-------------| | [ci-workflow.md](references/templates/ci-workflow.md) | GitHub Actions pipeline | | [deny-toml.md](references/templates/deny-toml.md) | Supply-chain policy + workspace root |
---
cargo fmt --all -- --check cargo clippy --all-targets --all-features -- -D warnings cargo deny check cargo audit cargo nextest run --all-features cargo test --doc cargo llvm-cov --all-features --workspace
# root Cargo.toml
[workspace.dependencies]
serde = { version = "1", features = ["derive"] }
# member Cargo.toml
[dependencies]
serde = { workspace = true }→ See [deny-toml.md](references/templates/deny-toml.md) for the complete root manifest
---
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).