Roasbeef

@roasbeef source repo

25 skills
0 followers
3 hours ago last updated

▌
Variant Analysis · roasbeef bundle
Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.

0
installs
▌
Calculator · roasbeef
Perform calculations and math operations. Use for arithmetic, conversions, or formulas.

0
installs
▌
Summarizer · roasbeef
Summarize text, documents, or conversations. Use when you need a concise overview.

0
installs
▌
Go Debug · roasbeef bundle
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".

0
installs
▌
Agent CLI · roasbeef
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.

0
installs
▌
Litbucket · roasbeef
Publish, search, and inspect internal Litbucket static artifacts. Use when asked to publish a site, dashboard, notebook, report, or other static bundle to an internal address, to find one that already exists, or to share a generated artifact with the team. Triggers include "publish this to litbucket", "put this on lightning.wiki", "find the <name> dashboard", "give me a link to this report".

0
installs
▌
Substrate · roasbeef
This skill provides agent mail management via the Subtrate command center. Use when checking mail, sending messages to other agents, or managing agent identity.

0
installs
▌
Nano Banana · roasbeef bundle
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.

0
installs
▌
Orchestrate · roasbeef bundle
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.

0
installs
▌
Review Loop · roasbeef bundle
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.

0
installs
▌
Test Refine · roasbeef bundle
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".

0
installs
▌
Advisor Review · roasbeef
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.

0
installs
▌
Explainer Video · roasbeef
Produce a narrated explainer video end to end — interview-driven, like /ideate but the output is a rendered mp4. Pipeline: script → TTS or recorded VO → Whisper word timestamps → Remotion scenes cued to the spoken word → headless 4K render. Use when asked to "make a video", "produce an explainer", or "turn this script/post into a video".

0
installs
▌
Decision Records · roasbeef bundle
Where a decision goes and how it is written down so the next reader finds it: architecture decision records (ADRs, amended by addendum and never by silent edit), protocol-change proposals for frozen interfaces, design notes with a status lifecycle, adversarial review waves with a triage roll-up, and corrections filed on the issue rather than only in a commit. Use when a decision was just made and needs a home, when an existing ruling needs revisiting, when a review wave is being filed, or with `init` to scaffold the whole decision layout in a repo that has none. Pairs with `handoff` (the next.md rewrite) and `doc-graph` (per-package docs).

0
installs
▌
Mutation Testing · roasbeef bundle
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".

0
installs
▌
Incremental Commit · roasbeef
Create incremental, atomic commits that tell a story with detailed commit messages. Use when the user asks to commit changes, split a diff into logical commits, or wants a clean commit history instead of one large commit. Triggers include "commit this", "make atomic commits", "break this into commits", "/incremental-commit".

0
installs
▌
Agentic Code Reasoner · roasbeef bundle
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.

0
installs
▌
Property Based Testing · roasbeef bundle
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.

0
installs
▌
Doc Gardening · roasbeef bundle
Maintain the per-package documentation graph (CLAUDE.md/AGENTS.md) and the architecture roll-up after code changes. Use when a new package was created, types/messages/dependencies changed significantly, after a large refactor, or when {{GATE_COMMAND}} fails.

0
installs
▌
Hunk · roasbeef
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.

0
installs
▌
Lnget · roasbeef
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.

0
installs
▌
Codify · roasbeef
Turns an observed agent misbehavior, or a correction the user just gave, into a durable fix: a hook that makes the behavior impossible, a CLAUDE.md rule, a change to the skill that was running, or a new reusable skill. Picks the narrowest home that removes the failure mode, checks for an existing rule to tighten before adding one, and keeps CLAUDE.md from bloating. Invoked via /codify when an agent goes off the rails on something the user does not want repeated.

0
installs
▌
Advisor · roasbeef
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.

0
installs
▌
CI Loop · roasbeef bundle
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.

0
installs
▌
Handoff · roasbeef bundle
Rewrite the repo's session handoff document (docs/next.md) at the end of a body of work: re-baseline every claim against the tree and CI rather than carrying it forward, name where the previous edition was wrong, record the rulings nobody should re-litigate and the gaps deliberately left open, and order what to do next with exit criteria. Also `init` to create the handoff and a starter docs/execution.md (how waves are planned, sub-agents briefed, and gates verified) in a repo that has neither. Use when finishing a milestone, a wave, or a PR series; when a fresh session cannot tell where the tree is; or when next.md and the code disagree. Pairs with `decision-records`.

0
installs

25 published skills