Modern Go development — stdlib-first code style with cobra/viper CLIs, table-driven tests and native fuzzing, canonical project layout with pinned tooling, documentation conventions with LLM-ready CLI references, and GoReleaser-based release engineering.
Go documentation conventions — a doc comment on every exported function, struct, type, and package, package comments in a dedicated doc.go for multi-file packages, godoc style (complete sentences beginning with the identifier's name), and LLM-ready CLI reference generation for cobra tools via a docgen helper built on cobra/doc. Use when writing or reviewing doc comments or godoc in Go code, documenting an exported Go API, package, function, or struct, deciding where a package comment or doc.go belongs, or generating markdown CLI documentation for a cobra-based Go tool.
Scaffold a Go project with the canonical layout — cmd/ entrypoints with a thin main, private packages under internal/, a separate tools module pinning Go developer CLIs (invoked directly via go tool, no GOBIN), Node tools pinned in package.json and run from node_modules/.bin, and a Makefile whose pr target runs the full local gate. Use when creating a new Go project, service, or repository, restructuring an existing Go repo to the standard layout, pinning Go or Node developer tooling, or adding standard Makefile targets (pr, fmt, vet, test, fuzz, build) to a Go codebase.
Release engineering for Go projects — GoReleaser v2 with version ldflags into an internal/version package, SBOMs and multi-arch container images, tag-triggered GitHub Actions releases, CI running build/vet/test -race/govulncheck with SHA-pinned actions, and Dependabot coverage for gomod, tools, npm, and Actions. Use when setting up releases or GoReleaser for a Go project, writing GitHub Actions CI or release workflows for a Go repository, stamping version metadata into a Go binary at build time, or adding Dependabot coverage to a Go repo.
Modern Go code style for stdlib-first programs — error wrapping with %w, sentinel errors, structured logging with log/slog, context threading, consumer-defined interfaces, nil-safe constructors, net/http servers with method-pattern routing, flag/env configuration for services, and cobra commands with viper configuration for CLI tools. Use when writing, reviewing, or refactoring Go code (.go files, packages, services), adding error handling or logging to a Go program, building a Go CLI tool or subcommands (cobra, viper), or deciding how to shape interfaces, constructors, configuration, or HTTP handlers in Go.
Go testing conventions — table-driven tests with t.Run subtests, plain stdlib assertions (no testify or assertion frameworks), hand-written fakes behind small interfaces, t.Helper() helpers, httptest for HTTP handlers, and native fuzz targets (testing.F) with seed corpora. Use when writing or reviewing Go tests (_test.go files), testing a Go HTTP handler, adding a fuzz test or seed corpus to a Go package, or choosing go test flags for a Makefile or CI (-race, -fuzz, -fuzztime).
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Agent skills and plugins from Bitwise Media Group, packaged as a marketplace for Claude Code, OpenAI Codex CLI, Google Antigravity, and OpenCode.
Skills follow the Agent Skills open standard (SKILL.md with portable frontmatter), live once
under plugins/<plugin>/skills/, and are delivered to each tool through its native mechanism — no duplicated content.
Modern, stdlib-first Go development conventions.
| Skill | What it does |
|---|---|
go-style | House style for Go: %w error wrapping, sentinels, log/slog, context threading, consumer interfaces, stdlib net/http, cobra + viper CLIs. |
go-docs | Doc comments on every exported identifier, package comments in doc.go, and LLM-ready CLI reference generation for cobra tools. |
go-testing | Table-driven tests with subtests, stdlib assertions, hand-written fakes, httptest, and native fuzz targets with seed corpora. |
go-project | Scaffolds the canonical layout: cmd/ + internal/, a pinned tools module (go tool -modfile=tools/go.mod), and a Makefile with the pr gate. |
go-release | GoReleaser v2 with version ldflags, SBOMs, multi-arch images, SHA-pinned CI (-race, govulncheck), and Dependabot coverage. |
Conventions and workflows for authoring reusable Terraform modules.
| Skill | What it does |
|---|---|
terraform-style | House style for HCL: collection types, resource naming, name_prefix, for_each toggles, variable/output grouping, null defaults, file layout. |
terraform-module | Scaffolds a new module with the canonical layout (terraform.tf, main.tf, variables.tf, outputs.tf, README.md) from commented templates. |
terraform-validate | The fmt → init/validate → tflint loop, with a bundled provider-agnostic tflint.hcl. |
/plugin marketplace add bitwise-media-group/skills
/plugin install terraform@bitwise
codex plugin marketplace add bitwise-media-group/skills
codex plugin add terraform@bitwise
Both read .agents/skills/ natively. Clone this repo and symlink the skills in:
./install.sh # project scope: ./.agents/skills/ in the current directory
./install.sh --global # user scope: ~/.agents/skills + ~/.gemini/skills
./install.sh --global --claude # also link ~/.claude/skills
./install.sh --copy ... # copy instead of symlink
Symlinked installs update on git pull. Alternatively,
npx skills add bitwise-media-group/skills works as a zero-clone installer;
install.sh is the supported path.
Each skill ships with evals under plugins/<plugin>/evals/<skill>/, run through the
evolve CLI (the EVOLVE make variable selects the binary):
make eval-static): frontmatter, manifests, version sync. Runs in CI on every push.make eval-trigger): does the skill activate for the right prompts and stay quiet for
near-misses? Real headless claude -p sessions.make eval-behavior): does following the skill produce correct artifacts? Graded
deterministically (terraform validate, tflint, file/regex checks) with an optional LLM judge for subjective
assertions.Tiers 1–2 run per provider model (MODELS=anthropic|openai|google|all or specific model ids) and record token usage per
eval via the provider token-counting APIs. Results land in each skill's committed results.json; make report
(evolve report) renders them into EVALUATION.md + EVALUATION.json (plugin-level rollup) and
plugins/<plugin>/EVALUATION.md (per-eval detail).
Tiers 1–2 cost tokens and run via the manual evals GitHub workflow or locally.
See AGENTS.md for repository conventions: layout, dual Claude/Codex manifests, frontmatter policy, and the eval requirements for new skills.
npx claudepluginhub bitwise-media-group/skills --plugin golangTerraform style conventions, module scaffolding, and fmt/validate/tflint workflows for authoring reusable modules.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification