claude-files

Final adversarial audit of finished work by one top-tier model (Fable 5 or Opus 4.8), in a single report-only pass across three axes: verify the load-bearing invariants (especially any you could NOT run locally), simplify without losing properties, and hunt for live variants of the bug shapes just fixed. You then verify each finding and act. Use as the closing gate on a substantive or risky change before calling it done, especially when part of it (a systest, a migration, a concurrency path) can't be validated locally. Distinct from /advisor (decision consult), /review-loop (multi-agent fix loop), and /variant-analysis (single-pattern sweep). Invoke via /advisor-review or after finishing hard-to-verify work.

Line-level git staging and non-interactive rebase for agents that know exactly which lines they changed. Use when you need atomic commits carved out of a larger diff, or when you need to squash/drop/reorder/reword commits without interactive prompts.

On-demand consultation of a higher-tier model (Opus 4.8 or Fable 5) from a cheaper executor session. Emulates the native advisor-tool pattern in Claude Code: keep the main loop on a cheap model (Sonnet 5) and call the expensive model rarely, via a focused consultation packet, for a plan/decision/'what am I missing' — not for code. Use when the executor is stuck, before committing to a plan, after repeated failed attempts at the same fix, or before a risky/irreversible change. Invoked via /advisor or when the executor recognizes a consult checkpoint.

Expensive planner (Opus 4.8 / Fable 5) decomposes a task into independent work items, a fleet of cheap Sonnet 5 (or Haiku 4.5) workers executes them in parallel via a Workflow, and the planner synthesizes the results. Emulates the native orchestrator pattern in Claude Code: keep the expensive model scarce (one planning pass, one synthesis pass) and the cheap model abundant (N parallel workers). Prefers a deterministic dynamic workflow when available; falls back to in-instance Task dispatch. Use when the user types /orchestrate or asks to decompose, fan out, or parallelize a task across independent workers.

Babysit CI after a push: a monitor→classify→remediate state machine that watches a run to completion, mechanically fixes trivial/build breakage, reproduces test failures locally to tell a flake from a real bug, reruns suspected flakes within a budget, hands reproduced failures to a fixer that commits a fixup and pushes, and loops until CI is green or it can justify a bail back to the user. Prefers a deterministic dynamic workflow when available; falls back to in-instance Task dispatch. Use when the user types /ci-loop or asks to watch/babysit/auto-fix CI for a pushed branch or PR until it's green.

Adversarial review→triage→fix loop until a cold verifier signs off. Fans out lens-specific reviewer subagents, verifies every finding against the code (killing false positives), auto-applies confirmed fixes as fixup commits, and repeats until a fresh verifier approves. Prefers a deterministic dynamic workflow when available; falls back to in-instance Task dispatch. Use when the user types /review-loop or asks to adversarially review-and-fix a change set, branch, or commit range until clean.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Clear-writing guide distilled from Steven Pinker's "The Sense of Style." Use when writing or revising prose that must be clear to a reader — documentation, design docs, specs, explanations, essays, emails, reports, RFCs, release notes — or when asked to make writing clearer, tighter, less academic, or less jargon-laden. Activate for "make this clearer", "tighten this", "why is this hard to read", "edit this for clarity", or any prose-quality pass.

Use lnget to fetch resources from L402-protected URLs that require Lightning payments. Covers basic fetching, payment limits (max cost, max routing fee), token cache management, and Lightning backend status. Use when an HTTP request returns 402 Payment Required and a Lightning micropayment is needed, or when downloading files behind a Lightning paywall.

Validates Go test suite quality through mutation testing using go-gremlins/gremlins. Mutates production code, runs the test suite against each mutant, and reports which mutants the tests fail to kill — exposing weak assertions that line coverage cannot detect. Use when evaluating test effectiveness, validating newly written tests, or improving test quality for mission-critical code (consensus, channel state, payment flows, crypto). Triggers: "mutation test", "are these tests strong", "validate test quality", "/mutation-testing".

Refines an existing Go test suite — removes trivial/duplicate tests, strengthens weak assertions, reshapes tests around invariants, and closes branch-coverage gaps. Uses code-guided coverage and (when available) gremlins mutation-testing survivor data rather than relying on line coverage alone. Use when test quality is uneven, after a test-generation pass, before opening a PR, or as a quality gate on critical paths (consensus, channel state, payment flows). Triggers: "refine these tests", "tests are bloated", "tighten assertions", "remove trivial tests", "audit test quality", "/test-refine".

Interactively debug Go programs in a single context using Delve (dlv) driven through tmux. Use when a bug requires runtime inspection — stepping through code, examining variables, walking goroutines, attaching to a live process, or debugging a hanging integration test — rather than just reading the source. Triggers include "step through this", "set a breakpoint", "attach to the running server", "why is this goroutine stuck", "debug this failing test".

This skill provides agent mail management via the Subtrate command center. Use when checking mail, sending messages to other agents, or managing agent identity.

Run and interact with lnd Lightning Network daemon in Docker. Use for Lightning development, testing payment channels on regtest, managing lnd containers, and calling lnd RPC endpoints (getinfo, connect, open/close channels, pay/receive). Supports bitcoind, btcd, and neutrino backends.

Design and review CLIs for AI agent consumption. Covers machine-readable output, input hardening against hallucinations, schema introspection, context window discipline, dry-run safety rails, and skill file packaging. Use when building new CLIs, adding agent support to existing CLIs, reviewing CLI designs for agent compatibility, or wrapping APIs as CLI tools. Triggers: agent CLI, CLI for agents, machine-readable CLI, agent-first CLI, CLI agent DX.

This skill enables deep, execution-free code analysis using the "Semi-Formal Reasoning" methodology. Use it for complex debugging, patch verification, or subtle logic questions where standard inspection might miss edge cases. It requires the generation of a "Reasoning Certificate" verifying logic paths before delivering a conclusion.

Provides guidance for property-based testing across multiple languages and smart contracts. Use when writing tests, reviewing code with serialization/validation/parsing patterns, designing features, or when property-based testing would provide stronger coverage than example-based tests. For Go code, uses pgregory.net/rapid as the primary PBT framework.

Writing style guide for Roasbeef's technical prose. This skill should be used when writing PR descriptions, commit messages, technical documentation, blog posts, or any written content that should match Roasbeef's established voice. Activate when creating PRs, drafting commit messages, writing release notes, or composing technical explanations.

Generate and edit images using Gemini's image generation API (Imagen 3). This skill should be used when creating images, illustrations, diagrams, editing existing images, or iteratively refining visual content through multi-turn conversations.

Transform written content (blog posts, newsletters, articles) into visual slide deck images. This skill should be used when converting text content into presentation format, creating slide graphics from outlines, or generating visual summaries of written material.

Run and interact with eclair Lightning Network daemon in Docker. Use for Lightning development, testing payment channels on regtest, managing eclair containers, and calling eclair API endpoints (getinfo, connect, open/close channels, pay/receive).

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.