Oneshot Scorer — Development agent for Claude Code
Silent coach that scores requirements quality in real time during discuss.
How to install Oneshot Scorer
Installs to ~/.claude/agents/victorl2-oneshot-framework-oneshot-scorer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/victorl2/oneshot-framework/HEAD/agents/oneshot-scorer.md -o ~/.claude/agents/victorl2-oneshot-framework-oneshot-scorer.md Restart Claude Code, or start a new session, for it to be picked up.
What Oneshot Scorer does
name: oneshot-scorer description: Silent coach that scores requirements quality in real time during discuss. Returns a compact JSON object with per-dimension scores, overall score, and (when asked) structured coaching guidance. Never speaks to the human directly. tools: Read, Grep color: purple
You are the Oneshot Requirements Scorer. You are spawned by `/oneshot start` to score a requirements draft and (when asked) to emit structured coaching guidance back to the Discuss Agent.Alternatives in Development
- Idor Hunter — IDOR / BOLA specialist (H1 #55, OWASP API1:2023) 812 ★
- Subdomain Enumeration — subfinder -d {domain} -silent sort -u subs.txt amass enum -passive -d {domain} subs.txt sort -u subs.txt -o su 213 ★
- Migrator — Specialized agent for migrating ADVPL procedural code to TLPP object-oriented code, modernizing legacy Protheu 136 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Oneshot Discuss
Interactive requirements gathering with the human operator. Asks focused clarifying questions, updates a requi
Oneshot Reviewer
Independent PR reviewer. Runs locally after a Oneshot run reaches completed (PR open AND required CI green). S
Reviewer Dispatcher
Selects the weakest dimension from the most recent merge-probability-scorer output and runs the matching speci
Gsd Advisor Researcher.Compact
Researches a single gray area decision and returns a structured comparison table with rationale. Spawned by di
Gsd Assumptions Analyzer.Compact
Deeply analyzes codebase for a phase and returns structured assumptions with evidence. Spawned by discuss-phas
Harness Checker
Fresh-context artifact evaluator for goal loops. Reads only final artifacts — never Maker reasoning or PROGRES
Related Skills
Armature Agent Review
Use after you have used a CLI, MCP server, API, SDK, hosted service, or web app during a task, to submit a sho
Prompt Coach Skill
Interactive prompt coaching and improvement
2026 Coach
Executive coaching skill for planning your 2026 using research-backed process goals. Works with Claude Code an