dev-kit

Plugin dev-kit from marketplace atalias-claude-marketplace in atalias-mkyle/claude-dev-kit. Commands read from the repo's manifest — 1 month ago.

Skills (9)

• conventional-commits

  Use when writing a commit message, reviewing a branch's commit history before PR, or when the user says "commit this", "stage and commit", "let's commit", or asks whether commits are clean. Formats all commit messages per the Conventional Commits spec and audits existing commit history on request.

• debug-playbook

  Use when debugging a reported bug, an unexpected behavior, a failing test that isn't obvious, or anything that starts with "why is X happening". Walks through a structured isolation approach instead of jumping straight to a guess-and-edit loop, which is the most common failure mode of agentic debugg

• dependency-audit

  Use when new dependencies have been added, before a release, when a security advisory mentions a package you use, or on a scheduled basis.

• deploy-check

  Use before deploying to any environment, when the user says 'ready to ship', 'can we deploy', 'let's release', or to gate a CI/CD pipeline.

• incident-response

  Use when something broke after a deploy, a production incident is active, or a rollback needs to be evaluated quickly.

• onboard

  Use when onboarding a new team member, starting work after a long break, or when asked "how do I get started" or "what's the state of this project".

• pr-checklist

  Use before opening a pull request, when the user says "ready to ship", "let's PR this", "check before I push", or asks for a self-review pass. Walks through a pragmatic pre-PR checklist that catches the things reviewers always catch, so reviewers can focus on the things only humans catch.

• project-bootstrap

  Use when the user wants to set up Claude Code on a new project, asks to "create a CLAUDE.md", "bootstrap claude", "initialize claude for this repo", or when there is no CLAUDE.md in the current project root yet and the user is starting work. This skill drops in a small, project-specific CLAUDE.md ba

• security-review

  Use when the user asks for a security review, security check, or wants to audit changes before merging — especially changes that touch auth, input handling, external API calls, file I/O, shell commands, or infrastructure configuration.

Slash commands (4)

• /dev-kit:bootstrap

  Set up Claude Code in the current project — drops a small CLAUDE.md and .claude/memory/decisions.md tailored to the stack

• /dev-kit:pr-check

  Run the pre-PR self-review checklist before pushing

• /dev-kit:refresh

  Re-run project-bootstrap in refresh mode — re-detects the stack and updates only the sections of CLAUDE.md that have drifted

• /dev-kit:security-check

  Run a security review on the current branch or a given PR

Subagents (11)

• ci-triager

  Use when a CI run on a PR or branch has failed and you need to understand why before deciding whether to fix, re-run, or escalate.

• debugger

  Use when there is a bug to diagnose, a test is failing and the cause is unclear, or a runtime error needs reproducing before fixing.

• implementer

  Use to execute an approved plan. Receives the plan from the planner (or directly from the user) and makes the code changes in an isolated context, returning a diff summary at the end. The implementer does not improvise scope — if the plan is wrong, it stops and asks instead of making it up.

• memory-curator

  Use at session end when significant architectural decisions were made, or when .claude/memory/decisions.md is growing large or may contain stale/contradictory entries.

• orchestrator

  Use when starting a non-trivial task from scratch, when you need the full dev pipeline run end-to-end, or when an agent returns blocked/partial and you need recovery routing.

• planner

  Use before implementing any feature, refactor, or non-trivial bug fix. The planner produces a written, reviewable plan that lists exactly which files change, in what order, with explicit risks and a rollback path. The main agent should hand off to the planner whenever the work spans more than a sing

• researcher

  Use proactively when a question requires reading multiple files, scanning a codebase, or exploring unfamiliar code. The researcher reads broadly and returns a compressed summary instead of polluting the main context with raw file dumps. Ideal first step before any non-trivial change.

• reverse-reasoner

  Use after the planner produces a plan and before the implementer runs, or on any non-trivial task before committing to an approach. The reverse-reasoner validates a plan or solution by running a forward pass (does the logic hold end-to-end?) and a backward pass (what must be true for the outcome to

• reviewer

  Use after the implementer finishes, before accepting the work. The reviewer is read-only — it reads the diff, checks against the plan, and flags issues. Treat its output the way you'd treat a colleague's PR review: useful, sometimes wrong, never automatically actioned.

• security-reviewer

  Use after the general reviewer on changes that touch authentication, authorization, user input handling, external API calls, file I/O, shell commands, or infrastructure configuration.

• test-runner

  Use to run the test suite and report failures. The test-runner runs tests, parses noisy output, and returns only the relevant failure information instead of dumping the whole log into the main context. Especially useful when tests take a while or produce a lot of output.

MCP servers (6)

• openviking

  connects to: ${user_config.openviking_base_url}/mcp

• context7

  runs: npx -y @upstash/[email protected]

• serena

  runs: sh -c uvx --from git+https://github.com/oraios/[email protected] serena start-mcp-server --context claude-code --project "$CLAUDE_PROJECT_DIR"

• sequential-thinking

  runs: npx -y @modelcontextprotocol/[email protected]

• brave-search

  runs: npx -y @modelcontextprotocol/server-brave-search

• memory

  runs: npx -y @modelcontextprotocol/server-memory

Hooks (9)

• PreToolUse

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pre_bash_guard.py ${user_config.enable_bash_guard}

• PreToolUse

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pre_write_guard.py ${user_config.enable_bash_guard}

• PostToolUse

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/post_edit_format.py ${user_config.enable_autoformat}

• UserPromptSubmit

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/openviking_recall.py

• SessionStart

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/setup_openviking.py ${user_config.openviking_base_url}

• SessionStart

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_context.py ${user_config.enable_session_context}

• SessionStart

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/openviking_session_start.py

• Stop

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_capture.py

• Stop

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/openviking_capture.py

Similar plugins