juliusbrussee/caveman
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 brief".
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 brief".
npx skills add https://github.com/juliusbrussee/cavekit/tree/main/skills/cavemanCaveman 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 brief".
This repo contains 4 individual skills — each has its own dedicated page.
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. Triggers on test failure, bug report, post-mortem, or explicit user ask.
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.
Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec. Phrasings: "check drift", "audit the spec", "does the code still match §V", "check invariants", "spec vs code".
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, distill a spec from existing code, add invariants, amend sections (§G, §C, §I, §V, §T, §B), or record a bug via backprop. Common phrasings: "write the spec for...", "new spec", "bug: ...", "amend §V.3", "distill spec from code", "spec this idea". Reads and follows FORMAT.md for the caveman encoding rules and pipe-table shape of §T and §B.
读后无书 · talk without book — methodology + 3 agentskills.io-compatible skills (Claude Code / Hermes / OpenClaw) to turn books into durable personal thinking infrastructure
Static lint + risk-hint auditor for AI Agent skill packs. Offline CLI, zero LLM, zero subprocess. Reads SKILL.md / CLAUDE.md / .cursor/rules/*.mdc and emits HTML/MD/JSON reports with deterministic scoring.
Compare multiple strategies or directions (long vs short vs both) on the same symbol. Generates side-by-side stats table.
Afu · LLM Todo: turn an Obsidian inbox into a living wiki, then into todo cards for this week.
for learn agent skill
EU AI Act compliance: scan, attest, document — from your IDE. Scanner catches code-verifiable violations, AI collects evidence for hybrid obligations, Human Gates capture pure attestations. Source-available (BSL 1.1), MCP-native, audit trail included.