@skills · Owner
Agent skills by juliusbrussee
50 skills indexed from github.com/juliusbrussee. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- cavecrew · Skill · 96,517 stars
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inlin
- cavecrew · Skill · 96,517 stars
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inlin
- caveman · Skill · 96,517 stars
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /c
- caveman · Skill · 96,517 stars
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /c
- caveman · Collection · 96,517 stars
- caveman · Collection · 96,517 stars
- caveman-commit · Skill · 96,517 stars
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
- caveman-compress · Skill · 96,517 stars
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
- caveman-compress · Skill · 96,517 stars
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
- caveman-help · Skill · 96,517 stars
Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".
- caveman-review · Skill · 96,517 stars
Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
- caveman-stats · Skill · 96,517 stars
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /cavem
- caveman-stats · Skill · 96,517 stars
Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.
- plugins · Collection · 96,517 stars
- skills · Collection · 96,517 stars
- skills · Collection · 96,517 stars
- backprop · Skill · 1,134 stars
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is
- build · Skill · 1,134 stars
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill befor
- cavekit · Collection · 1,134 stars
- caveman · Skill · 1,134 stars
Caveman encoding for SPEC.md and spec-adjacent writes. Loaded by /spec, /build, /check. Cuts tokens ~75% vs prose while staying precise. Triggers on any wr
- check · Skill · 1,134 stars
Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or
- deepen · Skill · 1,134 stars
Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper des
- grill · Skill · 1,134 stars
Calibrated interrogation of a fuzzy idea before it becomes a spec. Asks one question at a time, recommends an answer, and lands each answer in §G (goal) or
- research · Skill · 1,134 stars
Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library beh
- review · Skill · 1,134 stars
Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and
- skills · Collection · 1,134 stars
- spec · Skill · 1,134 stars
Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec. Triggers when the user asks to write a spec, start a new spec,
- caveman · Skill · 144 stars
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite,
- context-canary · Skill · 144 stars
Install a per-turn canary signal (e.g. starting every reply with the user's name and a turn counter) so silent context degradation becomes visible the mome
- grill-me · Skill · 144 stars
Calibrated grilling session for stress-testing a plan, design, idea, or decision. First assesses the user's topic knowledge, confidence, and desired pressu
- interface-kit · Skill · 144 stars
Authoritative guide for implementing stunning, accessible, performant UI. Synthesizes design engineering philosophy, accessibility standards, animation pri
- junior-to-senior · Skill · 144 stars
Adversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior rev
- last-20-percent · Skill · 144 stars
Finds and finishes the last 20% of a built solution — the experiential layer agents skip: what the output actually reads like, which pages or screens shoul
- loop-factory · Skill · 144 stars
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,
- skills · Collection · 144 stars
- skills · Collection · 144 stars
- caveman-discover · Skill
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaki
- caveman-evidence-review · Skill
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or wh
- caveman-explore · Skill
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or sym
- caveman-learn · Skill
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use w
- caveman-manage · Skill
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experimen
- caveman-optimize · Skill
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Cavema
- caveman-setup · Skill
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend
- deslopify · Skill
De-slop pass for any text. Scans for the statistical fingerprints of AI writing (negative parallelism / "not X but Y", em-dash density, rule-of-three, fals
- investigate-first · Skill
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-rank
- lean-build · Skill
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit
- migration · Skill
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and pr
- safe-refactor · Skill
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits
- surgical-patch · Skill
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests
- verify-and-stop · Skill
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile