Claude Technique Evaluator — Productivity skill for Claude Code
Evaluate new Claude prompting patterns, tools, or workflow changes.
How to install Claude Technique Evaluator
Installs to ~/.claude/skills/tstapler-dotfiles-claude-technique-evaluator/SKILL.md
mkdir -p ~/.claude/skills/tstapler-dotfiles-claude-technique-evaluator && curl -fsSL https://raw.githubusercontent.com/tstapler/dotfiles/HEAD/.claude/skills/claude-technique-evaluator.md -o ~/.claude/skills/tstapler-dotfiles-claude-technique-evaluator/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Claude Technique Evaluator does
name: claude-technique-evaluator description: Evaluate new Claude prompting patterns, tools, or workflow changes. Produces go/no-go recommendations and integration plans.
Claude Technique Evaluator
Evaluate new LLM techniques, tools, and workflow proposals for adoption value. Assess them against Anthropic standards and your local development workflow.
When to Use
- Use when: Evaluating a new prompting pattern, Claude Code configuration, tool integration (e.g., new MCP server
Alternatives in Productivity
- Reviews Plans — Review all active architecture plans relevant to the current task 15.6k ★
- Linear - Ticket Management — You are tasked with managing Linear tickets, including creating tickets from thoughts documents, updating exis 10k ★
- Tradingview MCP — Real-time crypto & stock screening, advanced technical indicators, Bollinger Bands intelligence, candlestick p 2.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Skillers
Learn from your workflow patterns and suggest skills, hooks, and agents. Analyze transcripts or get recommenda
Repo Watch
Mine the external repos in the watch registry for adoptable patterns and produce a prioritized adopt/defer rec
Jared Init
Bootstrap Jared on a project — introspect the board, write docs/project-board.md, run one-time migration of le
Agency
Run a B2B task across three bounded agents (Analyst / SDR / Auditor). The in-lane agent produces work; the oth
Eval Swarm
Fan every eval- evaluator agent across slices of the monorepo as a parallel swarm via the eval-swarm workflow
Eval
Run eval-driven development workflow. Execute verification loops and evaluate session outcomes against defined
Related Agents
Harness Evaluator
Use this agent when the harness needs to evaluate a generator's output. The evaluator interacts with the runni
Evaluator Fanout Child
Non-recursive evaluator-fanout leaf — tests one MCP-issued (bug_class × auth) cell, writes durable claim/cover
Cocotb Reviewer
cocotb testbench quality reviewer. Reviews Python test code quality, stimulus generation, assertion patterns,