Spec Review Local
Use when a brainstorming design spec has been written and needs adversarial review before implementation planning, using a local model served by LMStudio (via the pi CLI) as the independent reviewer. Works offline — no hosted API needed. Triggers on: spec review local, local spec review, review spec locally, lmstudio review, review spec, spec review.
Install
/plugin marketplace add adelrioj/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add adelrioj/claude-skills --skill spec-review-localgit clone --depth 1 https://github.com/adelrioj/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/spec-review-local ~/.claude/skills/spec-review-localPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Spec Review via pi (local LMStudio model) Adversarial review of design specs using a local `pi` agent backed by whatever model is currently loaded in LMStudio. Loops until the spec passes with zero CRITICAL and zero IMPORTANT findings. **Why a different agent:** The spec was written by this Claude instance. Self-review has author bias — the same blind spots that produced the issue prevent detecting it. The pi agent runs a different model (served locally by LMStudio at `http://127.0.0.1:1234`) with no shared conversation context, making it an effective adversarial reviewer. Pi has filesystem tools, so it verifies file paths and code references against the actual repo. **Sibling skill:** `spec-review-codex` does the same review with OpenAI Codex — use it when a hosted frontier model is preferred and available. --- ## The Job 1. Locate the spec file 2. Detect the loaded LMStudio model 3. Send to pi for adversarial review 4. Read findings 5. If verdict is NEEDS REVISION: fix the spec, loop back to step 3 6. If verdict is PASS: report clean to user 7. Maximum 3 review iterations (prevent infinite loops) **Do NOT** proceed to implementation planning until the spec passes review. **Prerequisite:** `pi` must be on PATH and LMStudio must be running at `http://127.0.0.1:1234` with at least one LLM loaded. Model detection (Step 2) verifies this — abort with a clear error if no model is loaded. --- ## Step 1: Locate the Spec
Details
- Skill name
spec-review-local- Repository
- adelrioj/claude-skills
- Path
skills/spec-review-local/SKILL.md- Repo updated
- 24 August 2026
FAQ
What does the Spec Review Local skill do?
Use when a brainstorming design spec has been written and needs adversarial review before implementation planning, using a local model served by LMStudio (via the pi CLI) as the independent reviewer. Works offline — no hosted API needed. Triggers on: spec review local, local spec review, review spec locally, lmstudio review, review spec, spec review.
How do I install the Spec Review Local skill?
Claude Code plugin: /plugin marketplace add adelrioj/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Spec Review Local popular?
It lives in adelrioj/claude-skills, which has 5 GitHub stars and 0 forks.
Related skills
Architect Review PR
5adelrioj/claude-skills
Use after a feature is built — e.g. the final step of a ship-it run, right after review-pr — to check it is actually complete and wired, not just line-correct. Dispatches a fresh-context Claude subagent that traces the whole repo to hunt completeness and integration gaps in the branch's changes, reports ranked, evidence-backed findings, then fixes the CRITICAL ones and verifies with a fresh re-review (capped at 3 passes; pass report-only to skip fixing). Triggers on: architect review, architecture review, completeness review, wiring review, is this wired, did we finish this, find the gaps, inc
Blind Spot
5adelrioj/claude-skills
Use BEFORE starting work on a task to surface the unknown-unknowns you're about to walk into but can't see. Dispatches a fresh-context Claude subagent that hunts what you don't know you don't know about the codebase, the domain, and the decisions ahead, calibrated to your stated experience, then reports ranked, evidence-backed findings and fixes nothing. Triggers on: blind spot pass, blindspot, unknown unknowns, what don't I know, what am I missing, help me prompt better, I know nothing about, teach me my unknowns, before I start, de-risk this task, surface my blind spots.
Claude Md Slim
5adelrioj/claude-skills
Use when CLAUDE.md has grown bloated and is taxing every session's context — the inverse of claude-md-improver. Triages each block into session-invariant rules (stay always-on) vs feature/subsystem detail (page out to docs/ behind a plain-path pointer), moving — never deleting — the detail so nothing is lost and the always-on token bill drops. Triggers on: slim claude.md, minimal claude.md, claude.md is bloated, shrink claude.md, split claude.md, make claude.md minimal, page out claude.md, claude.md too long, reduce project memory, point claude.md to docs, trim claude md.
Acquire Codebase Knowledge
9sandbaseai/workbuddy-skill
Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.
Spec Review Codex
5adelrioj/claude-skills
Use when a brainstorming design spec has been written and needs adversarial review before implementation planning, using OpenAI Codex as the independent reviewer. Requires the codex CLI. Triggers on: spec review codex, codex spec review, review spec with codex, codex review, review spec, spec review.
API Design Principles
9sandbaseai/workbuddy-skill
Use when designing, reviewing, documenting, versioning, or migrating REST or GraphQL APIs and their client, security, performance, and compatibility contracts.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.