Agent skills by JuliusBrussee

Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow.

JuliusBrussee/caveman

Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.

JuliusBrussee/caveman

Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.

JuliusBrussee/caveman

Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

JuliusBrussee/caveman

Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

JuliusBrussee/caveman

Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".

JuliusBrussee/caveman

Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact.

JuliusBrussee/caveman

After a bug is found, traces its root cause and feeds a new testable invariant back into the project spec so the bug class can't recur.

JuliusBrussee/cavekit

How to write and maintain DESIGN.md as the visual specification layer for Cavekit projects.

JuliusBrussee/caveman-code

Compresses SPEC.md writes and spec-referencing prose into terse, symbol-heavy fragments that drop articles, filler and hedging while keeping facts intact.

JuliusBrussee/cavekit

Cavekit specification-driven development methodology — the Hunt lifecycle (Draft → Architect → Build → Inspect → Monitor) and how to apply it.

JuliusBrussee/caveman-code

Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.

JuliusBrussee/caveman

Switches the agent's replies to terse Classical Chinese (wenyan) for the whole session, keeping code, commands, paths and numbers in their original form.

JuliusBrussee/caveman

Read-only detector that compares SPEC.md with the code and reports invariant, interface and task drift grouped by severity, without changing anything.

JuliusBrussee/cavekit

Trace bugs and manual fixes back to kits and prompts; fix at the source so the iteration loop can reproduce the fix autonomously.

JuliusBrussee/caveman-code

Install a per-turn canary signal (e.g. An agent skill from JuliusBrussee/skills.

JuliusBrussee/skills

Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report.

JuliusBrussee/caveman

Cuts the agent's replies down to bare fragments for the whole session, one word where one will do and no repeated facts, while code and error strings stay exact.

JuliusBrussee/caveman

Builds a skeptical reviewer grounded in the codebase and research notes to try to refute a spec before any code is written, citing file:line evidence and ending in a go or no-go gate.

JuliusBrussee/cavekit

Validation-first design for Cavekit — every kit requirement must be automatically verifiable.

JuliusBrussee/caveman-code

Adversarial senior-engineer review for agent-generated plans, designs, and architectures.

JuliusBrussee/skills

Authoritative guide for implementing stunning, accessible, performant UI.

JuliusBrussee/skills

Rewrites a memory file such as CLAUDE.md or a todo list in terse caveman-style text to cut input tokens, saving a readable backup outside the project tree.

JuliusBrussee/caveman-code

Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an…

JuliusBrussee/caveman

Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count…

JuliusBrussee/skills

Scaffold a complete cave plugin bundle — generates .cave-plugin/plugin.json manifest and the standard directory structure (commands/, skills/, agents/, themes/, hooks/).

JuliusBrussee/caveman-code

Scans the code a spec touches for its shallowest module, then proposes a refactor that hides more behind a smaller interface without changing behavior.

JuliusBrussee/cavekit

A read-only explorer for cold-start orientation or failed searches that replies with nothing but file path and line range citations, keeping its reads out of main context.

JuliusBrussee/caveman

Interrogates a vague idea one question at a time, recommending an answer each round and recording results as goals and constraints before a spec is written.

JuliusBrussee/cavekit

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing…

JuliusBrussee/caveman

Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback…

JuliusBrussee/caveman

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket…

JuliusBrussee/caveman

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant…

JuliusBrussee/caveman

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and…

JuliusBrussee/caveman

Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior.

JuliusBrussee/cavekit

Calibrated grilling session for stress-testing a plan, design, idea, or decision.

JuliusBrussee/skills

Creates, distills, amends and updates the project's SPEC.md from ideas, existing code or bug reports, as the only skill allowed to write that file.

JuliusBrussee/cavekit

De-slop pass for any text. An agent skill from JuliusBrussee/skills.

JuliusBrussee/skills