prompt-engineering
Design effective prompts using SPEARS framework — scope, principles, examples, assertions, refinements, with ReAct and multi-agent patterns
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-10
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- prompt-engineering
- triggers
- Improve prompt, security, ReAct, multi-agent
- changelog
- 2026-09-17
- description
- Design effective prompts using SPEARS framework — scope, principles, examples, assertions, refinements, with ReAct and multi-agent patterns
- token_budget
- 2630
03 SKILL.md 正文
Trigger: "improve prompt", "ReAct", "security", "multi-agent".
SPEARS: Scope — "for [ctx], in:[types], out:[format]"P: Principles — max 4 non-negotiable (security/quality/performance)E: Examples — 1 valid + 1 edge + 1 contraA: Assertions — ASSERT constraints | NEVER prohibitedR: Refinements — post-impl iterations
PATTERNS
ReActThought:[reason]→Action:[tool]→Observation:[result]...repeat→Final Answer
ReflexionTask:[task]→Attempt:[attempt]→Reflection:[crit]→Revision:[improved]...repeat
Multi-AgentRouter→Planner→Executor→CriticAgent: role, scope, tools, limitsComm: request→response, errors→reportingOrchestrator: routing→fallback→timeout
SECURITYINPUT: types/ranges/sanitizationOUTPUT: no-autoexec/rate limits/timeoutsDATA: no-creds/no-PII/no-tokensAGENT: least-privilege/tools schema/sandbox/human-in-loop
04 同仓库更多 Skills
web-quality-audit
Comprehensive web audit: performance, a11y, SEO, responsive, animation, design tokens.
ui-engine
UI system — Grid/Flexbox/@layer/:has(), container queries, compositor-only animation, OKLCH tokens, component patterns
baseline-ui
Anti-slop UI — layout, typography, responsive, animation, tokens. Use for cleanup or polish.
skill-creator
Create new AI agent skills following Agent Skills spec -- auto-bootstrap unknown tasks, define structure, register in AGENTS.md
senior-engineer
Apply senior engineering competencies — system design, trade-off analysis, delegation, mentoring, and tech debt strategy
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.