Summary
批判性评估默认规则,约束 Agent 在关键判断中检查目标、证据、假设、替代方案、风险与结论力度,并优先采用结构化思考、魔鬼代言人、反附和与立场偏见检查。适用于技术选型、架构设计、方案比较、优先级判断、公共争议分析等容易给出草率结论的场景。关键词:批判性思维、批判性评估、结构化思考、魔鬼代言人、反附和、立场分析、偏见识…
qiao-925/qiao-skills
批判性评估默认规则,约束 Agent 在关键判断中检查目标、证据、假设、替代方案、风险与结论力度,并优先采用结构化思考、魔鬼代言人、反附和与立场偏见检查。适用于技术选型、架构设计、方案比较、优先级判断、公共争议分析等容易给出草率结论的场景。关键词:批判性思维、批判性评估、结构化思考、魔鬼代言人、反附和、立场分析、偏见识别、证据、假设、替代方案、风险、结论力度。
npx skills add https://github.com/qiao-925/qiao-skills
批判性评估默认规则,约束 Agent 在关键判断中检查目标、证据、假设、替代方案、风险与结论力度,并优先采用结构化思考、魔鬼代言人、反附和与立场偏见检查。适用于技术选型、架构设计、方案比较、优先级判断、公共争议分析等容易给出草率结论的场景。关键词:批判性思维、批判性评估、结构化思考、魔鬼代言人、反附和、立场分析、偏见识…
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-p…
2 installsAuthor continuously-running online evaluations in PostHog AI observability, grounded in real fa…
2 installsImplement comprehensive evaluation strategies for LLM applications using automated metrics, hum…
39 installsPluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas…
25 installsAutomates the end-to-end detection engineering workflow in Google SecOps using MCP tools. Use w…
60 installsStructured scholarly-work evaluation for papers, proposals, literature reviews, methods section…
5.8K installsOther skills from qiao-925/qiao-skills · top by installs.
npx skills add https://github.com/qiao-925/qiao-skills
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main