Summary
当需要为目标 skill 生成改进候选、把上次失败信息注入下一轮生成、或分析历史记忆模式来避免重复失败时使用。支持 --trace 注入失败上下文。不用于打分(用 improvement-discriminator)或评估(用 improvement-learner)。
lanyasheng/auto-improvement-orchestrator-skill · Archived
当需要为目标 skill 生成改进候选、把上次失败信息注?
npx skills add lanyasheng/auto-improvement-orchestrator-skill --skill improvement-generator
当需要为目标 skill 生成改进候选、把上次失败信息注入下一轮生成、或分析历史记忆模式来避免重复失败时使用。支持 --trace 注入失败上下文。不用于打分(用 improvement-discriminator)或评估(用 improvement-learner)。
This repository is archived — consider an actively maintained alternative.
当需要把已批准的改进候选应用到目标文件、回滚之前的变更、或预览变更效果时使用。支持 4 种 action…
1 installs当需要为已有 Skill 自动生成 task_suite.yaml 测试任务集、从 skill_spec.yaml 生成完整 SKILL.md + …
1 installs当需要把多个功能重叠的 skill 合并为一个蒸馏版 skill 时使用。 不适用于从 skills 提取 rules(rule…
1 installsParse Claude Code session JSONL to extract implicit user feedback signals. Detects skill invoca…
1 installsRelated neighbors and high-traction skills in the same topics — useful to compare before installing.
Helps users discover and install agent skills when they ask questions like "how do I do X", "fi…
3.3M installsBrowser automation CLI for AI agents. Use when the user needs to interact with websites, includ…
810.4K installsReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…
617.3K installsBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …
576.5K installsPrepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Te…
568.3K installsOther skills from lanyasheng/auto-improvement-orchestrator-skill · top by installs.
npx skills add lanyasheng/auto-improvement-orchestrator-skill
Browse all from lanyasheng/auto-improvement-orchestrator-skill
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main
Parsed from SKILL.md frontmatter.
Files included with this skill beyond the listing page.
SKILL.md
5,136 B
README.md
80 B
SUMMARY.md
310 B
Produces ranked improvement candidates from target analysis, feedback signals, and failure traces.
improvement-discriminatorimprovement-learnerimprovement-orchestratorimprovement-executorimprovement-gate问题: 没有 trace 注入时,LLM 每次都从零开始生成候选。如果上一轮在 accuracy 维度失败了,下一轮很可能再次生成相同类别的候选 — 因为 LLM 不知道上次失败了。实测中无 trace 重试的重复失败率高达 60-70%。
Tradeoff: trace 注入增加了 prompt 长度(约 200-500 tokens),但大幅降低了重复失败率。Because trace 包含失败维度、失败原因、已尝试策略三个关键信号,generator 可以在生成阶段就避开已知死路,而不是等到 discriminator 打分后才发现。这比 "生成 → 打分 → 发现重复 → 重新生成" 的循环节省 1-2 轮迭代。
Previous failure on "accuracy" dimension
→ deprioritize candidates of the same category as the failed one
→ prioritize other dimensions' improvements instead
→ if same category failed ≥2 times, skip entirely and try adjacent dimensions
<example> 正确: 第一次失败后注入 trace 重试 $ python3 scripts/propose.py --target /path/to/skill --trace failure_trace.json --output candidates.json → 生成的候选会自动避开上次失败的 accuracy 维度策略 </example>
<anti-example> 错误: 失败后不注入 trace 直接重试 → 没有 trace 信息,generator 无法降低失败类别的优先级,容易重复生成同类候选 → 失败 ≥3 次的自动跳过逻辑在 improvement-learner 中,不在 generator </anti-example>
trace 文件记录上一轮失败的完整上下文,generator 解析后调整候选优先级:
{
"iteration": 2,
"failed_dimension": "accuracy",
"failed_category": "add_code_examples",
"failure_reason": "code example added but not syntactically valid",
"attempted_strategies": ["append_bash_example", "append_python_snippet"],
"scores_before": {"accuracy": 0.67, "coverage": 0.85},
"scores_after": {"accuracy": 0.63, "coverage": 0.85}
}
generator 收到这个 trace 后会:(1) 把 addcodeexamples 类别的优先级降到最低,(2) 从 coverage/triggerquality 等未失败维度寻找候选,(3) 如果 accuracy 下的其他类别(如 addoutput_artifacts)未尝试过则仍可生成。
# Basic generation
python3 scripts/propose.py --target /path/to/skill --output candidates.json
# With failure trace (retry loop)
python3 scripts/propose.py --target /path/to/skill --trace failure.json --output candidates.json
# With memory/feedback sources
python3 scripts/propose.py --target /path/to/skill --source memory.json --output candidates.json
| Request | Deliverable |
|---|---|
| Generate | JSON array of ranked candidates with category, risklevel, executionplan |
| With trace | Same format, priorities adjusted based on failure analysis |
| With memory | Candidates informed by historical patterns and past successes |
| With feedback | Candidates prioritized by user correction hotspots |
每个候选的 JSON 结构包含 category(改进类别)、risklevel(low/medium/high)、executionplan(具体修改步骤)、priorityscore(0-1 综合优先级)、traceadjusted(是否被 trace 调整过优先级)。