Skill Scorecard Analyst — Development agent for Claude Code
Reviews collected skill telemetry and recommends keep / refine / merge / deprecate per skill, with the evidence behind each call.
How to install Skill Scorecard Analyst
Installs to ~/.claude/agents/amiable-dev-skills-telemetry-skill-scorecard-analyst.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/amiable-dev/skills-telemetry/HEAD/agents/skill-scorecard-analyst.md -o ~/.claude/agents/amiable-dev-skills-telemetry-skill-scorecard-analyst.md Restart Claude Code, or start a new session, for it to be picked up.
What Skill Scorecard Analyst does
name: skill-scorecard-analyst description: Reviews collected skill telemetry and recommends keep / refine / merge / deprecate per skill, with the evidence behind each call. Use when asked to review skill performance, analyse the scorecard, decide which skills to retire, or explain why a skill's cost or pass rate changed. tools: Bash, Read, Grep, Glob
You analyse standards-telemetry data and make a keep / refine / merge / deprecate recommendation for each skill. You are the analysis half
Alternatives in Development
- Tend — Tend the Allium garden 3.7k ★
- Command Helper — Smart command assistant that understands user intent and suggests relevant commands 587 ★
- Thermo Nuclear Code Quality Review — Independent strict maintainability reviewer for a collected diff and changed-file contents 144 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Permission Analyst
Recommends allow/deny permission rules from denial telemetry and policy via PromptWise. Use to reduce permissi
Call Scorer
Scores one sales or discovery call transcript against SPIN, Gap Selling, the Trust Equation, yellow lights, JO
Mod Builder
Creates and changes Claude Code mods — plugins of function hooks behind a pane, band, status line, slash comma
Dbg Mistake Tracker Agent
Recurring error catalog. Use when asked 'what mistakes keep happening', 'recurring
Follow Up Agent
Use to keep warm conversations from going cold: stalled threads after an accept or a maybe, people who asked t
PR Reviewer.Agent
Use when asked to review a PR, diff, or set of changes — 'review this', 'code review', 'what's wrong with this
Related Skills
F1 Race Strategy Agent
CSE 598 Agentic AI capstone baseline — an agentic F1 race-strategy engineer: a Claude tool-use loop that recom
Setup Scorecard
Per-strategy expectancy scorecard from journal reviews and get_performance, with promote, restrict, or retire
Session Optimizer
Cross-platform prompt refinement for Codex, Gemini CLI, and Claude Code, plus Claude-native context guard and