Julius BrusseeCreator of caveman, 115k+ GitHub stars2,700 installs on skills.sh

Build

Plan-then-execute implementation against SPEC.md.

Use in my agent
Use Edge to load the skill build from juliusbrussee/cavekit for my task. If Edge is not set up, read getedge.cc/SKILL.md and ask me first.
Works in any agentClaude CodeCodexCursorClaude appChatGPT+ any other agent
juliusbrussee/cavekit
Security state: reviewed

2 static scans, 0 counted findings.

Edge checks it again each time your agent loads it.

SKILL.md1 file · 3.1 KB

From the juliusbrussee public repository. Edge did not write or edit this skill.

What it does

  • Plan-then-execute implementation against SPEC.md.
  • Native single-thread loop, no sub-agents.
  • On test or build failure, auto-invokes the backprop skill before retrying : a failed verification always considers whether a new §V invariant would prevent recurrence.
  • Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`).
  • Expects SPEC.md to exist; if not, defers to the spec skill.
JB

Why Julius Brussee

Founding engineer at Stacklink; data science student at Leiden. Each fact links its public source.

  • caveman, 115k+ stars

    His caveman repository, a Claude Code skill, has over 115,000 GitHub stars.

    GitHub repo
  • cavekit, 1.1k+ stars

    His follow-on cavekit repository has over 1,100 GitHub stars.

    GitHub repo
  • Founding engineer at Stacklink

    His site lists him as founding engineer at Stacklink, an enterprise RAG platform.

    personal site

Public sources, checked Oct 26, 2026.

How it works

  1. 1
    Copy

    Try for free gives you one prompt.

  2. 2
    Paste

    Paste it into Claude Code, Codex or Cursor.

  3. 3
    Ask

    Ask for the outcome. Your agent loads Build.

Related skills

DC
Speckit Implement
dceoy

Execute the implementation plan by processing and executing all tasks defined in tasks.md

JU
Backprop
juliusbrussee

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 the one non-obvious thing SDD does that plan-then-execute doesn't

JU
Caveman
juliusbrussee

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 write to SPEC.md or when user says "caveman", "compress this", "be

MA
Implement Spec
mattpocock

Implement a specification in code.

+23K installs this week
FE
Video Spec Builder
feicaiclub

当用户说想做一个视频、宣传片、产品演示、动画短片、抖音/YouTube 内容,或者说要改分镜、调节奏、换镜头、调字幕、加配音、改转场时使用。通过苏格拉底式追问收集视频需求,主动激发渲染层的全部能力(TTS / 字幕 / 3D / shader / 音频反应等),输出标准化的 video-spec.md 用于渲染。

DC
Speckit Plan
dceoy

Execute the implementation planning workflow using the plan template to generate design artifacts.

Evidence

No evidence record yet

No measured run with and without this skill yet, so this page makes no performance claim. 2 static scans, 0 counted findings. Security state at 2026-11-18: reviewed. Static scans check the code, not how well the skill works.

State definitions
SKILL.md3,177 bytes · Open on GitHub

Skill details

Security scansReviewed

2 static scans, 0 counted findings. Security state at 2026-11-18: reviewed. Edge checks it again each time your agent loads it.

Edge static checks (Edge-run): edge-static/1.0.2. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: not supplied.

Edge committed-secret checks (Edge-run): edge-secrets/1.0.0. Scope: Credentials committed in the skill's files (values never shown). Raw findings: not supplied.

Socket (skills.sh mirror): Version unavailable. Scope: Not supplied by the mirrored record. Raw findings: not supplied.

Snyk (skills.sh mirror): Version unavailable. Scope: Not supplied by the mirrored record. Raw findings: not supplied.

Edge static checks
Pass · 0 counted findings · 2026-11-18
Edge committed-secret checks
Pass · 0 counted findings · 2026-11-18
Creator, source & licencejuliusbrussee

From the juliusbrussee public repository. Edge did not write or edit this skill.

Revision
7421e87d5b517c415c519ddf58a3dd10ba842530
Package hash
sha256:3b2b36f27bf1f76c610b45a1d9cd05a3fdd927579c34ccd8e62390abb5122ac8
Licence
MIT
Description
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying : a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
Quoted from the skill’s own description
Read skill files1 file

1 file, 3.1 KB at revision 7421e87d5b51.

Questions about Build

What does Build do?

Plan-then-execute implementation against SPEC.md. Published by Julius Brussee (juliusbrussee/cavekit).

Is Build safe to use?

Edge security state: Reviewed (2 Edge-run static scans, scanned Nov 18, 2026). The Evidence tab shows the scan.

How do I use Build in Claude Code, Codex or Cursor?

Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.