huangpustar/metainfer/bound-the-gain-first
Claude Code and agent skill by huangpustar/metainfer
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
投入实现前先用理论模型估算收益上限,分母用实测可达值而非纸面峰值。上限低于噪声带的方向直接放弃。
Install
npx vskill@latest install huangpustar/metainfer/bound-the-gain-firstSKILL.md
先算收益上限再投入
何时触发:选择优化方向、决定为一个想法投入实现之前。
规则
- 用理论模型估算改动收益上限:理想耗时 ≈ max(计算量 ÷ 峰值算力, 数据量 ÷ 可达带宽);据此算出该方向最多能赚多少。
- 分母用实测可达上限做锚点(先跑一个理论上只受该资源限制的探针),不用纸面规格——纸面峰值会把效率系统性估低、把收益上限系统性估高。
- 上限低于噪声带的方向直接放弃——这是成本最低的一次假设否定。
- 多个可行方向按"预期收益 × 成功概率 ÷ 实现成本"排序,只做排头,其余入队。
- 多组件组合的性能问题:先测单组件可达上限,组合实测与单组件之和的差值即交互开销。
- 锚点远低于历史值时,先怀疑环境劣化(降频/共享/争用),再怀疑代码。
反模式信号
- 实现数天后才发现理论上限只有百分之几,前期投入全部沉没。
- 拿纸面峰值算出"还有 5 倍空间",实际可达上限早已贴住。
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingatomic-skills/bound-the-gain-first/SKILL.md
Popularity
- Repository stars
- 123
- Repository forks
- 17
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/huangpustar/metainfer/bound-the-gain-first)