ai-engineer: Public Skills (20)
Sorted by GitHub stars of the source repo, highest first.
| # | Skill | Owner | Repo | Stars | License | What it does |
|---|---|---|---|---|---|---|
| 1 | agent-eval | affaan-m | affaan-m/ECC | 302,998 | MIT | Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency... |
| 2 | agent-self-evaluation | affaan-m | affaan-m/ECC | 302,998 | MIT | Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability,... |
| 3 | eval-harness | affaan-m | affaan-m/ECC | 302,998 | MIT | Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, grade with... |
| 4 | healthcare-eval-harness | affaan-m | affaan-m/ECC | 302,998 | MIT | Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical... |
| 5 | scientific-thinking-scholar-evaluation | affaan-m | affaan-m/ECC | 302,998 | MIT | Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and... |
| 6 | claude-api | anthropics | anthropics/skills | 194,585 | null | - Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting,... |
| 7 | skill-creator | anthropics | anthropics/skills | 194,585 | null | Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch,... |
| 8 | scholar-evaluation | K-Dense-AI | K-Dense-AI/scientific-agent-skills | 57,202 | MIT | Provides qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics... |
| 9 | advanced-evaluation | sickn33 | sickn33/agentic-awesome-skills | 49,710 | MIT | Design LLM-as-judge rubrics, direct scores and pairwise comparisons. Use for judge models, evals, position bias and calibration against... |
| 10 | agent-evals | sickn33 | sickn33/agentic-awesome-skills | 49,710 | MIT | Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features,... |
| 11 | agent-evaluation | sickn33 | sickn33/agentic-awesome-skills | 49,710 | MIT | Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or... |
| 12 | agent-evaluation-reporting | sickn33 | sickn33/agentic-awesome-skills | 49,710 | MIT | Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and... |
| 13 | agent-observability | sickn33 | sickn33/agentic-awesome-skills | 49,710 | MIT | Instrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging. |
| 14 | eval-harness-first | wshobson | wshobson/agents | 42,512 | MIT | Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model... |
| 15 | evaluation-methodology | wshobson | wshobson/agents | 42,512 | MIT | PluginEval quality methodology, covering dimensions, rubrics, and scoring formulas. Use this skill when understanding how plugin quality is... |
| 16 | eval-genius | davila7 | davila7/claude-code-templates | 33,617 | MIT | - Decide whether an AI/LLM/agent/retrieval system needs an eval, where it fits in the dev process, which one to run, and how to read the... |
| 17 | evaluation-bigcode-evaluation-harness | davila7 | davila7/claude-code-templates | 33,617 | MIT | Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code... |
| 18 | evaluation-lm-evaluation-harness | davila7 | davila7/claude-code-templates | 33,617 | MIT | Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality,... |
| 19 | evaluation-nemo-evaluator | davila7 | davila7/claude-code-templates | 33,617 | MIT | Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when... |
| 20 | prompt-engineering-dspy | davila7 | davila7/claude-code-templates | 33,617 | MIT | Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy -... |
Links
- Up: ai-ml/applied-ai
- Seed skills: ai-engineer seed skills