技能提升
- 作者仓库星标 29
- 许可证 MIT
- 作者仓库 ai-engineering
- 领域
- 人工智能
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 100 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @arcasilesgroup · MIT
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 运行环境要求
- Python
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
/ai-skill-improve ai-plan # evolve one skill
/ai-skill-improve all --dry-run # preview every skill
/ai-skill-improve all # batch evolve with evals
# ai-skill-improve
## Quick start
```
/ai-skill-improve ai-plan # evolve one skill
/ai-skill-improve all --dry-run # preview every skill
/ai-skill-improve all # batch evolve with evals
```
## Workflow
Improve existing skills using evidence from real project pain (prior eval corpora under `.ai-engineering/evals/`, Engram cross-session observations via `MemoryPort`, `LESSONS.md` operator notes, decision-store, instincts, proposals). The skill owns pain diagnosis and rewrite strategy; it delegates the eval/grade/benchmark pipeline to Anthropic's `skill-creator`. **Output is PR-comment only — never auto-merged** (sub-007 M6).
1. **Phase 0.5** — load corpora (`.ai-engineering/evals/<skill>.jsonl`), Engram observations (`/ai-memory` MCP), and `LESSONS.md` H3 sections that mention the target skill.
2. **Phase 1** — load remaining pain context (decision-store, observations.yml, proposals.md).
3. **Phase 2** — analyze the target skill, score the 5 dimensions.
4. **Phase 3** — generate test prompts that exercise the failing pattern.
5. **Phase 4** — rewrite the skill (Start-Here, pain-injection, scope-gates, structured classification).
6. **Phase 5** — emit the proposed SKILL.md diff as a PR comment via `gh pr comment`. **Do not commit or push.** Operator review is the merge gate.
7. **Phase 6** — verify improvement on the operator's branch (pass-rate delta vs prior iteration).
> Detail: see [audit document skeleton](references/output-skeleton.md), [the six-phase protocol (load → analyze → generate → rewrite → eval → verify)](references/six-phase-protocol.md), [batch mode for `all`](references/batch-mode.md).
## When to Use
- A skill keeps producing bad output despite correct instructions.
- You've accumulated corrections in LESSONS.md that a skill should already know.
- After a batch of sessions where the same skill pattern failed repeatedly.
- Periodic hygiene: evolve the top 10 skills once a month.
- NOT for creating new skills from scratch — use `/ai-scaffold`.
- NOT for platform audit — use `/ai-ide-audit`.
Step 0 (load contexts): read `.ai-engineering/manifest.yml` `providers.stacks`; load `.ai-engineering/overrides/<stack>/conventions.md` for each stack and `.ai-engineering/overrides/_shared/conventions.md`; load `.ai-engineering/team/*.md` for team conventions.
## Common Mistakes
- Rewriting before reading the pain profile.
- Skipping `--dry-run` on batch (you'll burn rate limits).
- Inventing test prompts that mirror the skill's own examples (no drift signal).
- Leaving Phase 5 evals unrun and declaring the skill "improved".
## Examples
### Example 1 — single-skill evolution from accumulated pain
User: "the /ai-plan skill keeps producing decomposition that ignores constraint X. Improve it."
```
/ai-skill-improve ai-plan
```
Loads pain context from LESSONS.md and proposals.md, scores ai-plan on 5 dimensions, generates 2-3 test prompts that exercise the failing pattern, rewrites SKILL.md, hands off to skill-creator for eval, reports the delta.
### Example 2 — dry-run batch preview
User: "preview what improving every skill would change before I commit time to running evals"
```
/ai-skill-improve all --dry-run
```
Walks every skill in priority tier order, shows the proposed diff per skill, and stops short of running the eval pipeline.
## Integration
Reads: decision-store.json, LESSONS.md, observations.yml, proposals.md, manifest.yml. Writes: target SKILL.md files. Calls: `python scripts/sync_command_mirrors.py` after rewrites. Delegates to: Anthropic `skill-creator` (eval/grade/benchmark, Phase 5). Feeds into: `/ai-learn`. See also: `/ai-scaffold` (new skills), `/ai-ide-audit` (cross-IDE).
$ARGUMENTS
章节与文件索引
按说明文件中的顺序排列。
工作流程
何时使用
常见错误
示例 1——从累积的痛苦中进化出单一技能
示例 2 — 试运行批量预览
文件/命令 -> .ai-engineering/evals/ · MemoryPort · LESSONS.md · skill-creator · .ai-engineering/evals/<skill>.jsonl · /ai-memory · gh pr comment · all
内容校验值 -> 2a10be9e6082
当前原文的自动摘译,尚未人工审校。
工作流程
使用来自真实项目痛点的证据来提高现有技能(
.ai-engineering/evals/下的先前评估语料库,通过MemoryPort、LESSONS.md操作员笔记、决策存储、直觉、建议进行印迹交叉会话观察)。该技能拥有疼痛诊断和重写策略;它将评估/等级/基准管道委托给 Anthropic 的skill-creator。输出仅是 PR 评论——从不自动合并(sub-007 M6)。何时使用
尽管指令正确,但技能仍会产生错误的输出。您已经在 LESSONS.md 中积累了技能应该已经知道的更正。经过一批相同的技能模式重复失败的训练后。定期卫生:每月发展一次十大技能。不适合从头开始创造新技能——使用
/ai-scaffold。常见错误
在阅读疼痛概况之前重写。在批次中跳过
--dry-run(您将消耗速率限制)。发明反映技能自身示例的测试提示(无漂移信号)。不运行第 5 阶段评估并声明技能“已改进”。示例 1——从累积的痛苦中进化出单一技能
用户:“/ai-plan 技能不断产生忽略约束 X 的分解。改进它。”从 LESSONS.md 和proposals.md 加载疼痛上下文,在 5 个维度上对人工智能计划进行评分,生成 2-3 个测试提示来练习失败模式,重写 SKILL.md,交给技能创建者进行评估,报告增量。
示例 2 — 试运行批量预览
用户:“在我投入时间运行评估之前预览改进每项技能会发生什么变化”按优先级顺序遍历每项技能,显示每项技能建议的差异,并停止运行评估管道。