Token导航 LogoToken导航

Agent Skill · 研究检索

compile(compile 搜索)

compile 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

compile 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 57,864。

总安装 423周安装 18GitHub Stars 318下载 148核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:compile(compile 搜索)
来源仓库:https://github.com/boshu2/agentops
仓库路径:skills/compile
安装命令:
npx skills add https://github.com/boshu2/agentops --skill compile
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/boshu2/agentops --skill compile

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

compile 用于将 .agents/ 中的原始工件编译成结构化的、相互关联的 Markdown 知识库。适用于需要从现有代码和文档中提取信号,并生成可验证、可链接的知识文章的场景。通过 /compile 命令触发,自动处理 git 历史和工件文件,输出结构化知识库。

需确认项目是否有 .agents/ 目录及写入权限,避免误改系统文件。compile 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/compile

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/boshu2/agentops --skill compile;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

compile 怎么安装?

在终端执行 npx skills add https://github.com/boshu2/agentops --skill compile。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

compile 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

compile 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

compile 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

compile 用的人多吗?

公开数据是累计安装 423 次,近一周安装 18 次,下载 148 次,GitHub 318 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

compile 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
compile

compile 搜索 · 本页

423318接触敏感数据未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Compile — Knowledge Compiler

Reads raw .agents/ artifacts and compiles them into a structured, interlinked markdown wiki. Inspired by Karpathy's LLM Knowledge Bases.

What This Skill Does

The knowledge flywheel captures signal reactively (via /retro, /post-mortem, /forge). /compile closes the loop by:

  1. Mining unextracted signal from git and .agents/ (existing)
  2. Growing learnings via validation, synthesis, and gap detection (existing)
  3. Compiling raw artifacts into interlinked wiki articles (NEW — the core value)
  4. Linting the compiled wiki for contradictions, orphans, and gaps (NEW)
  5. Defragging stale and duplicate artifacts (existing)

No vector DB. At personal scale (~100-400 articles), the compiled wiki fits in context windows. The wiki IS the retrieval layer.

Output: .agents/compiled/ — encyclopedia-style markdown with [[backlinks]], index.md catalog, and log.md chronological record.

Pluggable Compute Backend

Set AGENTOPS_COMPILE_RUNTIME to choose the LLM backend:

ValueBackendNotes
claude-cliLocal claude binaryZero-config. Inherits your Claude Code auth — no API key needed. Auto-selected if claude is on PATH and nothing else is set.
ollamaOllama APIDefault model: gemma3:27b. Set OLLAMA_HOST for remote (e.g., ssh -L 11435:localhost:11435 bushido-windows).
claudeClaude API (HTTP)Uses ANTHROPIC_API_KEY. Model: claude-sonnet-4-20250514.
openaiOpenAI-compatibleUses OPENAI_API_KEY + OPENAI_BASE_URL.
(unset)Claude Code sessionCompilation happens inline via the current session's LLM.

When AGENTOPS_COMPILE_RUNTIME is unset, ao compile first tries to auto-detect a local claude binary (claude-cli runtime). If that is also absent, headless compile fails fast with an explicit error naming the env var to set. Interactive /compile invocations still run compilation prompts inline — the agent reading this SKILL.md IS the compiler.

Runtime preference (override auto-detect)

To force a non-auto-detected runtime permanently (e.g. you have claude installed but prefer Ollama for privacy), set it in ~/.agentops/config.yaml:

compile:
  preferred_runtime: ollama

Precedence (high → low): --runtime flag, AGENTOPS_COMPILE_RUNTIME env, compile.preferred_runtime config, claude-binary auto-detect, empty (error).

Large-corpus batching

ao compile passes --batch-size to the headless compiler (default 25 changed files per LLM prompt). A fresh run against a 2000+ file corpus will split into batches automatically instead of sending one giant prompt.

Flags:

  • --batch-size N — files per batch (default 25)
  • --max-batches N — cap batches per invocation; remaining files are picked up on the next run (default 0 = unlimited)

Execution Steps

Phase-by-phase detail lives in references/phases.md. Summary of modes:

  • /compile — Full cycle: Mine → Grow → Compile → Lint → Defrag
  • /compile --compile-only — Skip mine/grow, just compile + lint
  • /compile --lint-only — Only lint the existing compiled wiki
  • /compile --defrag-only — Only run defrag/cleanup
  • /compile --mine-only — Only run mine + grow (legacy behavior)

The steps are:

  1. Mine — extract signal from git + .agents/research/ + complexity hotspots
  2. Grow — LLM-driven validation, synthesis, gap detection; adjust learning confidence
  3. Compile — inventory → topic extraction → wiki articles with [[backlinks]]
  4. Lint — contradictions, orphans, missing cross-refs, stale claims
  5. Defrag — prune stale, dedup near-duplicates, sweep oscillating goals, normalization scan
  6. Report — write .agents/compile/YYYY-MM-DD-report.md

See references/phases.md for the full per-phase procedure, confidence-scoring table, auto-promotion rules, template shapes for article / index / log / lint-report / compile-report, and the normalization defect scan.

Scheduling / Auto-Trigger

Lightweight defrag (prune + dedup, no mining or compilation) runs automatically at session end via the compile-session-defrag.sh hook. This keeps the knowledge store clean without requiring manual /compile invocations. The hook:

  • Fires on every SessionEnd event after session-end-maintenance.sh
  • Skips silently if the ao CLI is not available
  • Runs only ao defrag --prune --dedup (no compilation or mining)
  • Has a 20-second timeout to avoid blocking session teardown

For full compilation, invoke /compile manually or schedule the headless compiler script with your host OS:

# Example: external cron entry for nightly compilation on bushido
0 3 * * * cd /path/to/repo && AGENTOPS_COMPILE_RUNTIME=ollama bash skills/compile/scripts/compile.sh --force

AgentOps exposes this flow through ao compile. If you want unattended compilation, use your host scheduler (launchd, cron, systemd, CI, etc.) to invoke ao compile --force --runtime ollama or call the lower-level bash skills/compile/scripts/compile.sh directly. If you want the broader private overnight loop, use ao overnight start instead of inventing a parallel Dream wrapper inside /compile.

Interactive Modes

These modes describe the interactive /compile skill behavior:

ModeDescription
--compile-onlySkip mine/grow, just compile + lint
--lint-onlyOnly lint the existing compiled wiki
--defrag-onlyOnly run defrag/cleanup
--mine-onlyOnly run mine + grow (legacy behavior)
--fullFull cycle: mine → grow → compile → lint → defrag
--since 26hTime window for the mine phase
--incrementalSkip unchanged source files (hash-based)
--forceRecompile all articles regardless of hashes

Headless Script Flags

For unattended runs, bash skills/compile/scripts/compile.sh supports:

FlagDefaultDescription
--sources <dir>.agentsSource root for learnings, patterns, research, retros, forge, and knowledge
--output <dir>.agents/compiledTarget directory for compiled wiki output
--incrementalonSkip unchanged source files (hash-based)
--forceoffRecompile all articles regardless of hashes
--lint-onlyoffOnly run the lint pass on the existing compiled wiki
--fullonAccepted for parity; default behavior already runs the full headless compile path

Examples

User says: /compile — Full Mine → Grow → Compile → Lint → Defrag cycle.

User says: /compile --compile-only — Just compile raw artifacts into wiki.

User says: /compile --lint-only — Scan existing wiki for health issues.

User says: /compile --since 7d — Mines with a wider window (7 days).

Scheduled externally: Nightly compilation on bushido GPU via Ollama.

Pre-evolve warmup: Run /compile before /evolve for a fresh, validated knowledge base.

Troubleshooting

ProblemCauseSolution
ao mine not foundao CLI not in PATHUse manual fallback in Step 1
No orphaned researchAll research already referencedSkip 2b, proceed to synthesis
Empty mine outputNo recent activityWiden --since window
Oscillation sweep emptyNo oscillating goalsHealthy state — no action needed
Ollama connection refusedTunnel not running or wrong hostRun ssh -L 11435:localhost:11435 bushido-windows or check OLLAMA_HOST
Compilation too slowLarge corpus on small modelUse --incremental or switch to larger model
Hash file missingFirst compilationNormal — full compile runs, hashes saved after

Reference Documents

平台分布

Codex

35.39%
按下载量换算52

Claude

26.97%
按下载量换算40

Cursor

19.7%
按下载量换算29

Gemini CLI

8.62%
按下载量换算13

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills