Agentpack Skill Review — Development skill for Claude Code
Review an existing agent skill and generate a balanced trigger/non-trigger eval set with a reproducible iteration workspace.
How to install Agentpack Skill Review
Installs to ~/.claude/commands/vishal2612200-agentpack-agentpack-skill-review.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/vishal2612200/agentpack/HEAD/.claude/commands/agentpack-skill-review.md -o ~/.claude/commands/vishal2612200-agentpack-agentpack-skill-review.md Restart Claude Code, or start a new session, for it to be picked up.
What Agentpack Skill Review does
description: Review an existing agent skill and generate a balanced trigger/non-trigger eval set with a reproducible iteration workspace.
AgentPack Skill Review
Use when the user invokes `/agentpack-skill-review ` or asks to review, improve, benchmark, or generate evals for a skill.
Usage
/agentpack-skill-review skills/example/SKILL.md
/agentpack-skill-review example-skill
Workflow
- Run
agentpack skill-review --skill "$ARGUMENTS" --jsonand r
Alternatives in Development
- Jupyter Notebook — Create clean, reproducible Jupyter notebooks for experiments and tutorials 14.6k ★
- Autoresearch — Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code 2.5k ★
- Learn Review — Manually trigger a learning review of the current session 172 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Auto Trigger
After any recon/probe step, route observed signals to the right tools and fire the auto-plan (Balanced policy)
Analyze No Shows
Analyzes Chili Piper meeting no-show patterns by trigger type, routing path, rep, or workspace to surface acti
Sdd Clarify.Prompt
Re-run or manually trigger the sdd-clarify phase for an existing change.
Pc Update
Produce OLD→NEW find/replace edits that bring an existing product_context.md to its current decided state from
Codify
Load phase 05 (codify) for the current workspace. Update existing agents and skills with new knowledge.
Copy User
Copies a user's Chili Piper workspace and team memberships (and, optionally, product licenses) to another exis
Related Agents
Eval Failure Analyzer
Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a skills-works
Workflow Orchestrator
Fallback router when user intent is unclear, or when a global state snapshot and next-step recommendation is n
AI Eval Designer
Use this agent to design a risk-tiered evaluation set for an AI feature. Trigger when the user says "design ev