swarmstr

Analyze and document codebase architecture: dependency graphs, module boundaries, API surfaces, tech debt. Use when: (1) user asks 'how is this codebase structured', (2) onboarding to a new project, (3) planning a large feature that spans modules, (4) identifying tech debt or coupling issues. NOT for: specific code changes (use refactor), reviewing a PR (use code-review).

Structured code review for PRs, diffs, or changed files. Use when: (1) reviewing a pull request, (2) checking code quality before merge, (3) auditing changes for correctness/security/performance, (4) user asks to review code or a diff. NOT for: debugging failures (use debug), running tests (use verify), or general code reading.

Manage dependencies: audit outdated packages, resolve conflicts, evaluate alternatives, handle breaking upgrades. Use when: (1) updating dependencies, (2) resolving version conflicts, (3) checking for vulnerabilities in deps, (4) evaluating a new library. NOT for: general code changes, security vulnerabilities in own code (use security-audit).

Generate or update documentation: API docs, README, CHANGELOG, ADRs. Use when: (1) user asks to document code, (2) writing a README for a new project, (3) updating docs after a change, (4) creating architecture decision records. NOT for: inline code comments (just add them), reviewing docs (use code-review).

Advanced git operations: rebase strategies, cherry-pick workflows, bisect automation, worktree management, conflict resolution, branch cleanup. Use when: (1) complex git operations beyond basic add/commit/push, (2) resolving merge conflicts, (3) reorganizing commit history, (4) managing multiple working branches. NOT for: basic git (use git tools directly), GitHub API operations (use github skill).

Language-specific idiom guides for Go, Python, TypeScript, Rust. Covers non-obvious patterns: project layout, error handling, testing idioms, build quirks, common pitfalls. Use when: (1) writing code in a specific language and need idiomatic patterns, (2) user asks 'what's the Go/Python/etc way to do X', (3) porting code between languages. NOT for: syntax questions (the model already knows syntax).

Performance profiling and analysis: identify hot paths, memory leaks, N+1 queries, benchmark before/after. Use when: (1) user reports slowness, (2) optimizing a critical path, (3) benchmarking changes, (4) diagnosing memory issues. NOT for: general debugging (use debug), code review (use code-review).

Refactor code: extract functions, rename symbols, move modules, split files, inline variables, reduce duplication. Use when: (1) user asks to refactor, (2) code needs restructuring without behavior change, (3) extracting reusable components, (4) cleaning up after a feature is stable. NOT for: adding features (that's coding), fixing bugs (use debug), style-only changes.

Audit code for security vulnerabilities: injection, secrets, auth bypass, insecure deps. Use when: (1) reviewing code for security, (2) user asks about security of a change, (3) checking for leaked secrets, (4) assessing new API endpoints. NOT for: general code review (use code-review), performance issues (use perf-profile).

Generate comprehensive test suites for functions, modules, or APIs. Use when: (1) user asks to write tests, (2) new code lacks test coverage, (3) adding edge case or regression tests, (4) user says 'test this'. NOT for: running existing tests (use verify), debugging test failures (use debug).

Bitcoin and Lightning Network protocol knowledge for agents with wallet access. Use when: agent needs to send/receive lightning payments, check balances, create invoices, understand BOLT-11, convert between sats/BTC, evaluate fees, or decide which payment tool to use (NWC vs Cashu vs zaps). NOT for: on-chain Bitcoin transactions, mining, or running a node (see lnd-node-ops and bos-node-ops skills).

Balance of Satoshis (bos) advanced LND node management. Use when: rebalancing channels, accounting, probing routes, managing peers with scoring, liquidity analysis, fee optimization, or automated node operations. Requires bos CLI (Node.js) + LND access. NOT for: basic lncli operations (use lnd-node-ops), making payments (use bitcoin-lightning), or LNbits admin (use lnbits-admin).

LNbits server administration via its REST API. Use when: managing wallets, extensions, node channels/peers through LNbits, or checking LNbits server status. Requires LNbits admin or super-user API key. NOT for: making payments (use bitcoin-lightning skill), direct node CLI (use lnd-node-ops skill).

LND Lightning node operations via lncli. Use when: managing channels, peers, routing fees, liquidity, backups, or diagnosing node issues. Requires lncli binary with macaroon access. NOT for: making payments (use bitcoin-lightning skill), LNbits admin (use lnbits-admin skill), or bos workflows (use bos-node-ops skill).

Triage incoming messages and tasks into structured workflows. Classify priority, route to appropriate flows, and ensure nothing falls through the cracks.

Orchestrate multi-step durable workflows above background tasks. Create, monitor, and manage task flows that survive restarts and track progress across sequential or branching steps.

Debug a failing runtime, test, or integration path by collecting concrete evidence before proposing fixes.

Review swarmstr memory entries, propose cleanup, and separate durable pinned knowledge from ordinary stored notes.

Review recent changes for duplication, unnecessary complexity, and avoidable work, then clean them up.

Turn a repeatable workflow from the current session into a reusable SKILL.md for swarmstr/metiq.

Verify that a change actually works by running the relevant tests or end-to-end checks.

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/.metiq/workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Search and analyze your session index to look up past sessions by date, channel, or user.

Local text-to-speech via sherpa-onnx (offline, no cloud)

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Nostr Improvement Proposals (NIPs) reference. Use when implementing, verifying, or explaining any Nostr protocol — event kinds, encryption schemes, relay behaviour, identity, payments, DVMs, git, etc. Read the specific NIP file before writing protocol-level code.