SkillCheatSheet
llm-evaluation
An AI agent skill from davila7/claude-code-templates, scored 57 out of 100 by code.
Code score by group
It loses the most points in Description (15), the group that checks whether the description says what the skill does and when to use it.
What the author says it does
Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.
- Repository
- davila7/claude-code-templates
- Folder
- cli-tool/components/skills/ai-research/llm-evaluation
- License
- MIT
- GitHub stars
- 33,382
- SKILL.md lines
- 488
- Other files
- 0
Add llm-evaluation to your agent
npx skills add davila7/claude-code-templates --skill llm-evaluationThe command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.
More skills from davila7/claude-code-templates
-
session-handoff
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capac…
Verified88A -
five-whys
Use for the 5 Whys, or when the user wants the root cause of a failure: "why did this happen?", "this keeps breaking", "write the postmortem", "find the real cause". Asks why repe…
Verified87A -
premium-web-design
Create premium, Awwwards-quality website designs as React (.jsx) components that look like they were built by a top-tier agency charging $50k+ per project. Use this skill whenever…
87A -
thinking-method-selector
Use when the user describes a problem, decision or stuck situation but names no method: "how should I approach this?", "help me think this through", "we can't decide", "where do I…
Verified84B -
pre-mortem
Use for a pre-mortem, or before committing to a plan, launch or migration: "what could go wrong?", "stress test this plan", "how might this fail?", "risks before we ship". Assumes…
Verified83B -
render-deploy
Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or se…
Verified83B -
worktree-cleaner
Inventory the git worktrees of the current repository, classify each one with evidence (merged, PR state, uncommitted or unpushed work, locked, stale, in use by a running session)…
Verified83B -
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or…
Verified83B
All skills in davila7/claude-code-templates
Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.