prompt-tuner
Improve embedded LLM system prompt based on evaluation test failures
浏览 wildcard 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
17收录技能的仓库 Stars 合计
377仓库 Forks
30平均每个技能的仓库 Stars
22同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Improve embedded LLM system prompt based on evaluation test failures
Validates code changes against the project's consolidated knowledge and configuration rules. Use on push to catch violations of agreed-upon standards like installation scripts, linking patterns, and configurati...
Use when users need help generating safe, tested POSIX shell commands from natural language descriptions. Guides users through command generation, safety validation, and execution workflows using Caro best prac...
This skill should be used when the user asks to "run beta test cycle", "run next cycle", "test static patterns", "analyze test failures", "improve pass rate", or wants to systematically improve command generati...
Quality Engineer Manager skill for orchestrating release validation, beta testing coordination, feedback analysis, and release sign-off decisions
Expert on multicultural heritage traditions, holidays, and celebrations. Use for maintaining holiday theme features, adding new cultural events, ensuring cultural sensitivity, and managing the data-driven holid...
Systematic audit of safety patterns to identify gaps, regressions, and improvement opportunities
Guide for integrating safety validation into new inference backends
Suggests which benchmarks to run based on code changes
Use when fixing issues identified in beta tester feedback. Guides systematic root cause analysis, worktree-based fixes, regression testing, and release preparation. Invoke with structured beta reports or issue...
Analyze brownfield codebase and create initial continuity ledger
Verify debug/dev artifacts are removed before commit. Use at session end to apply 'good boy scout' rule - leave code cleaner than you found it.
Guide through TDD process for adding new safety patterns - from threat identification to commit
Document leftover tasks as GitHub issues with full correlation to branch, PR, and original work plan. Use when ending a session with incomplete work that another agent should pick up.
Use when users need to simulate unbiased beta testers for CLI tools. Creates tester personas, models their environment, and runs terminal-first exploratory testing based only on documentation and observed termi...
Implement AI-powered statusline with session tracking, plan detection, workspace emojis, and intelligent caching for Claude Code
This skill should be used when the user asks to "set up shell completions", "fix zsh completions", "configure tab completion", "add completions for brew/npm/cargo", "troubleshoot missing completions", or mentio...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。