evaluation-driven-development
Skill5 starsChanged 37 days agoAGPL-3.0View on GitHub
评测驱动开发 / Evaluation-driven development：AI需求不稳定，需要用可复现评测指导构建迭代。交付edd-plan.md，包含证据、决策与失败处置。
In this repository59 other files it gives its agents.
- agent-designSkill
- guardrail-designSkill
- human-in-the-loopSkill
- memory-designSkill
- multi-agent-designSkill
- tool-designSkill
- workflow-designSkill
- permission-modelSkill
- rag-architectureSkill
- system-architectureSkill
- ai-opportunity-mappingSkill
- ai-scenario-prioritizationSkill
- cost-assessmentSkill
- enterprise-ai-pricingSkill
- roi-assessmentSkill
- value-difficulty-matrixSkill
- delivery-handoverSkill
- enterprise-acceptanceSkill
- project-retrospectiveSkill
- sla-designSkill
- docker-deploymentSkill
- go-live-checklistSkill
- poc-to-productionSkill
- private-deploymentSkill
- production-acceptanceSkill
- ai-maturity-assessmentSkill
- enterprise-ai-diagnosisSkill
- pain-point-analysisSkill
- 30-day-industry-learningSkill
- ai-scenario-discoverySkill
- business-process-mappingSkill
- customer-discoverySkill
- customer-interviewSkill
- field-observationSkill
- industry-researchSkill
- stakeholder-mapSkill
- context-engineeringSkill
- mcp-designSkill
- observability-designSkill
- prompt-designSkill
- agent-task-evaluationSkill
- ai-security-testingSkill
- eval-dataset-generationSkill
- golden-dataset-designSkill
- hallucination-evaluationSkill
- prompt-regressionSkill
- rag-evaluationSkill
- tool-calling-evaluationSkill
- chunk-strategySkill
- data-quality-assessmentSkill
- knowledge-base-designSkill
- retrieval-strategySkill
- source-inventorySkill
- ontology-designSkill
- poc-scopeSkill
- prd-generationSkill
- requirement-to-pocSkill
- solution-briefSkill
- technical-solution-designSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.