Spec Anchor — Testing skill for Claude Code
Spec governance and anti-decay layer for AI coding agents.
How to install Spec Anchor
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open linziyanleo/spec-anchor and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Spec Anchor does
Spec governance and anti-decay layer for AI coding agents.
Alternatives in Testing
- Spec Kitty — Spec-Driven Development for serious software developers 1.6k ★
- Spec Driven Develop — Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub 975 ★
- Spectra App — Spec-driven development for coding agents — a desktop app, a CLI, and skills for Codex, Claude Code, Cursor, C 735 ★
README
SpecAnchor
Spec is the anchor, code is the ship.
English · 中文 · WHY · Install · Contributing · Skill
What SpecAnchor Is
**SpecAnchor is a three-tier spec system that agents load on boot.** It keeps your team's coding rules, module contracts, and task intents in `.specanchor/`, then agents load the relevant ones into context before any code is generated — and check later whether the code still matches.
Think of it as a **Context Construction System** for AI coding agents: it compiles bounded, auditable, sedimentable engineering context across four categories — **Spec / Decision / Evidence / Finding** — into a *Context Bundle* that every agent reads before acting, detects drift through an *Alignment Surface*, sediments ac
Related Skills
Atomic Spec
Stop your AI from vibe-coding. Governance layer that forces Claude, Cursor, Copilot, Gemini & 13 more through
GAAI Framework
95+ Drop-in governance layer (.gaai/ folder) -- backlog authorization, cross-session memory, decision tracking
Intent Planner
Pre-spec steering layer for AI coding agents — capture product intent, invariants, and decision criteria befor
Geekstack Flow
A structured AI workflow for planning, coding, reviewing, testing and shipping software — LLM wiki memory, a t
Skeleton First Code Skill
AI coding agent workflow skill: long-context memory, anti-amnesia pipeline (Plan→Implement→Test), module tree
Test TypeScript
Run TypeScript tests for Solana frontends and Anchor programs
Related Agents
Architecture Debt Analyzer
Analyzes architecture debt — circular dependencies, God modules, tight coupling, layer violations, missing sep
Registry Auditor
Audit the AgtMLS registry for drift, spec violations, routing decay, and stale generated artifacts without cha
Mp Alignment Auditor
Read-only, fresh-context audit of a merged masterplan plan against the ORIGINAL user request. Consumes goals.m