bstack

Use when cataloging a repository's externally observable capabilities as end-to-end scenarios and driving them through test, fix, and re-test until verified

Use when explicitly asked to "handoff", "인수인계", or "write a handoff" to preserve context for the next session.

Use when setting up Claude Code global configuration on a new machine — CLAUDE.md, settings.json, statusline.sh, worktree configuration

Use Jira through a slim Atlassian MCP facade for issue lookup, triage, creation, comments, and lightweight status reporting.

Use when writing, reviewing, or improving PRDs, product requirements documents, product specs, feature requirements, launch requirements, or product discovery writeups before product or engineering work begins.

Use when writing, reviewing, or improving RFCs, requests for comments, technical design docs, architecture proposals, engineering decision records, API proposals, migration plans, or cross-team technical decisions.

Use the Datadog pup CLI for logs, monitors, APM, metrics, and incident investigation.

Write and update Notion pages or database entries through the official Notion MCP server.

Search Notion workspace content through the official Notion MCP server.

Draft, format, and send Slack messages through the official Slack MCP server.

Search Slack through the official Slack MCP server for messages, files, channels, users, and thread context.

Create PR — commit, push, PR, wait for merge.

Use when exploring unfamiliar codebases, investigating bugs, checking external documentation, or learning unfamiliar technology before acting

Use when asked to "evolve skill", "스킬 개선", "회고", or "analyze this session". Builds a transcript index, validates real-world scenarios with subagents, and proposes small patches to SKILL.md / AGENTS.md / CLAUDE.md with user approval.

Use when asked to "qa", "verify this", "does this implementation work?", or "test this feature". Verifies the current implementation in context and reports `PASS`, `PARTIAL`, or `FAIL` with evidence.

Set up and run an autonomous experiment loop for any optimization target. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".

Use when preparing to deploy to production, asked to "ship", "release", or "deploy", or when you need to verify a deploy succeeded or plan a rollback. Covers the full flow: pre-deploy checks, the deploy itself, and post-deploy verification with rollback on failure.

Review code changes for correctness, readability, architecture, security, performance, and test coverage using subagents.

Design, run, and improve tests for a change using project conventions and subagent verification.

Use when changes span multiple components, services, or layers and unit/integration tests alone cannot confirm the full flow works correctly

Use when designing systems, architectures, or APIs, when multiple valid approaches exist with no single obvious answer, or when user explicitly requests parallel/competing solutions