xobotyi/cc-foundry

coding

Language-agnostic coding workflow: discovery, change decomposition, commit sizing, comment and naming policy, and completion evidence.

bun

Write and review Bun: the Bun-native API surface against its `node:` equivalents, the HTTP and WebSocket server, file and process I/O, the shell, the data clients, `bun:test`, the bundler and compiled binaries, and the package manager.

nodejs

Write and review Node.js: the module system, package manifest, streams, event loop, process and worker lifecycle, the permission model, native TypeScript execution, `node:test`, and the runtime version `engines.node` permits.

vitest

Write and review Vitest tests: structure, assertions, fixtures and lifecycle, the mocking surface and its hoisting rules, snapshots, configuration and projects, pools and isolation, coverage, type tests, and migration from Jest.

javascript

Write and review JavaScript: declarations, equality and coercion, functions, objects, iteration, classes, async and promise semantics, ES modules, regular expressions, JSDoc typing, and the ECMAScript features a project's engine baseline permits.

typescript

Write and review TypeScript: the type system, strictness configuration, narrowing, generics, type-level patterns, declaration files, module resolution and `tsconfig`, and the release a project's compiler pins.

frontend-design

Decide and verify what a web interface looks like: reuse of the existing design, color, type, layout, controls, states, and interface copy that trace to the product instead of a framework or model default.

humanize

Remove AI-writing tells from reader-facing prose and prevent them while drafting: the mechanisms that produce the tells, the thresholds that mark a passage, and the edit that fixes the text without flattening its author.

networking

Write and review network configuration for self-hosted Linux infrastructure: what an nftables ruleset, a resolver zone, a reverse-proxy site, a forward-auth chain, a WireGuard or Tailscale tunnel, or an IDS rule does once loaded, where that differs from what…

ansible

Write, review, and run Ansible: the ansible-core line a project pins, what the 2.19 templating engine refuses, which task results are claims rather than measurements, where a variable's value comes from, and what ansible-lint and Molecule prove.

devops

Carry an infrastructure change from intent to verified effect: what a change must carry before apply, what "applied" does not prove, which changes a revert cannot reverse, what a credential can do that the instruction never said, and the evidence that closes…

task-creation

Write and review work items in an issue tracker: establish which reader the item is for, verify every claim it makes against the system, and give the implementer a location and acceptance criteria. Sizing and decomposition belong to tasks.

tasks

Work item decomposition — break implementation phases into sized, dependency-mapped tasks, each producing a verifiable artifact. Invoke whenever task involves the T stage of the DRAFT pipeline, decomposing phases into tasks, or creating a task breakdown.

youtrack

Work YouTrack as an agent: what a project configures rather than fixes, what a write changes besides the field it names, and which failures report success. Not what a work item should say.

issue-writing

Prepare issues for repositories you do not maintain: route the report to the right channel, meet the project's evidence bar, and supply the elements maintainers want most. The user files it. Not for opening pull requests.

pr-contribution

Prepare pull requests for repositories you do not maintain: find the project's AI-contribution rules before writing code, earn a reviewer, and shape the change so a volunteer can say yes. The user opens the PR. Not for filing issues.

output-style-engineering

Design and maintain Claude Code output styles: choosing the mechanism, setting the frontmatter, and writing the role, voice, and rules the style installs in the system prompt.

commit

Git commit workflow pipeline: atomic unit identification, commit ordering, quality gates, message validation, and post-commit verification.

commit-message

Git commit message conventions: structure, formatting, scoping, body content, breaking changes, trailers.

handoff

Triage this conversation into a standalone transfer document — decisions, constraints, resource identifiers, verification state, and remaining work — for a session restart or a teammate.

claude-md

Write and maintain CLAUDE.md and `.claude/rules/` files: which layer loads when, what content belongs in each, and why a stated rule gets ignored.

zog

Write and review Zog schema validation in Go: schema shape, Parse against Validate, required and default semantics, tests and transforms, issue handling, and the zhttp, zjson, and zenv adapters.

charm-tui

Write and review Charmbracelet v2 terminal UIs in Go: Bubble Tea programs, Bubbles components, Lip Gloss styling and layout, Huh forms, Glamour markdown, fang CLI entry, and TUI testing.

templ

Write and review templ templates: syntax, components, attributes, styling, JavaScript data passing, escaping and sanitization, code generation, and testing.

golang

Write and review Go: idioms, error handling, concurrency, testing, project structure, the toolchain, and the language version a module's `go` directive permits.

subagent-engineering

Design and maintain Claude Code subagents: the delegation decision, the frontmatter that governs a run, and the system prompt the agent wakes up with.

prompt-engineering

Write and debug instruction text on any surface: requests, standing context such as CLAUDE.md, tool and schema descriptions, and prompts written for other model instances.

prompt-terser

Run a phased terseness pass over an existing prompt or skill and return a diff-proposal: mechanical wording and format cuts listed as applied, structural cuts gated behind a falsification check.

skill-engineering

Author and maintain Agent Skills: routing metadata, body content, bundled references and scripts, evaluation, and distribution.

python

Python language conventions, modern idioms, and toolchain. Invoke whenever task involves any interaction with Python code — writing, reviewing, refactoring, debugging, or understanding Python projects.

cli

CLI application design: argument conventions, output streams, exit codes, configuration hierarchy, interactive modes, and terminal UX. Invoke whenever task involves any interaction with command-line tools or terminal applications — building, reviewing,…

shell-scripting

Shell script conventions, defensive patterns, and correctness rules: strict mode, quoting, portability, error handling, and common pitfalls. Invoke whenever task involves any interaction with shell scripts — writing, reviewing, debugging, or understanding…

release

GitHub release creation for cc-foundry plugins: per-plugin tags, release notes as the changelog, and post-push publishing. Invoke whenever task involves pushing commits to master, releasing or publishing a plugin version, bumping plugin versions, or writing…

research

Objective codebase investigation — factual findings about existing code, patterns, and architecture. Invoke whenever task involves the R stage of the DRAFT pipeline, technical codebase research, or understanding existing code before design.

dashboards

Grafana dashboard authoring: JSON model (Classic and V2), panel types and selection, standard options, thresholds, value mappings, field overrides, transformations, variables (query/custom/interval/filter), repeating panels and rows, annotations,…

alignment

Solution direction synthesis — design opinions from research findings, presented for human correction, with decision capture. Invoke whenever task involves the A stage of the DRAFT pipeline, aligning on approach before implementation, or recording design…

discovery

Requirements elicitation and validation through structured questioning. Invoke whenever task involves defining what to build, scoping a problem or feature, or starting the DRAFT pipeline.

frame

Vertical-slice implementation planning — phases that cross all layers end-to-end with per-phase testing. Invoke whenever task involves the F stage of the DRAFT pipeline, planning implementation phases, or structuring work before coding begins.

pest

Pest testing framework conventions and practices. Invoke whenever task involves any interaction with Pest — writing function-style tests (test/it/describe), the expect() expectation API, datasets, hooks, architecture/mutation/type-coverage/browser testing,…

glossary

Project glossary for consistent domain terminology. Invoke whenever task involves creating, updating, or referencing a glossary, defining domain terms, establishing ubiquitous language, or when inconsistent naming causes confusion in code or planning…