← 返回 Skills 市场
756
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install code-cache
功能描述
Semantic code caching for AI agents. Cache, retrieve, and reuse code from prior agent executions.
使用说明 (SKILL.md)
Code Cache - Semantic Code Caching for AI Agents
This skill enables semantic code caching via the Raysurfer API.
What It Does
When your agent generates and executes code, Code Cache stores it. When a similar task comes up later, the agent can retrieve and run the cached code instead of regenerating it—saving time and tokens.
Setup
Get your API key from the Raysurfer dashboard and configure it:
# Via environment variable
export RAYSURFER_API_KEY=your_api_key_here
# Or via OpenClaw config
openclaw config set skills.entries.code-cache.apiKey "your_api_key_here"
Available Commands
Search for cached code
/code-cache search \x3Ctask description> [--top-k N] [--min-score FLOAT] [--show-code]
Search for cached code snippets that match a natural language task description.
Options:
--top-k N— Maximum number of results (default: 5)--min-score FLOAT— Minimum verdict score filter (default: 0.3)--show-code— Display the source code of the top match
Example:
/code-cache search "Generate a quarterly revenue report"
/code-cache search "Fetch GitHub trending repos" --top-k 3 --show-code
Get code files for a task
/code-cache files \x3Ctask description> [--top-k N] [--cache-dir DIR]
Retrieve code files ready for execution, with a pre-formatted prompt addition for your LLM.
Options:
--top-k N— Maximum number of files (default: 5)--cache-dir DIR— Output directory (default:.code_cache)
Example:
/code-cache files "Fetch GitHub trending repos"
/code-cache files "Build a chart" --cache-dir ./cached_code
Upload code to cache
/code-cache upload \x3Ctask> --files \x3Cpath> [\x3Cpath>...] [--failed] [--no-auto-vote]
Upload code from an execution to the cache for future reuse.
Options:
--files, -f— Files to upload (required, can specify multiple)--failed— Mark the execution as failed (default: succeeded)--no-auto-vote— Disable automatic voting on stored code blocks
Example:
/code-cache upload "Build a chart" --files chart.py
/code-cache upload "Data pipeline" -f extract.py transform.py load.py
/code-cache upload "Failed attempt" --files broken.py --failed
Vote on cached code
/code-cache vote \x3Ccode_block_id> [--up|--down] [--task TEXT] [--name TEXT] [--description TEXT]
Vote on whether cached code was useful. This improves retrieval quality over time.
Options:
--up— Upvote / thumbs up (default)--down— Downvote / thumbs down--task— Original task description (optional)--name— Code block name (optional)--description— Code block description (optional)
Example:
/code-cache vote abc123 --up
/code-cache vote xyz789 --down --task "Generate report"
How It Works
- Cache Hit: When you ask for code similar to something previously executed, Code Cache returns the cached version instantly
- Cache Miss: When no match exists, your agent generates code normally, then Code Cache stores it for future use
- Verdict Scoring: Code that works gets 👍, code that fails gets 👎—retrieval improves over time
API Reference
The skill wraps these Raysurfer API methods:
| Method | Description |
|---|---|
search(task, top_k, min_verdict_score) |
Unified search for cached code snippets |
get_code_files(task, top_k, cache_dir) |
Get code files ready for sandbox execution |
upload_new_code_snips(task, files_written, succeeded, auto_vote) |
Store new code after execution |
vote_code_snip(task, code_block_id, code_block_name, code_block_description, succeeded) |
Vote on snippet usefulness |
Why Code Caching?
LLM agents repeat the same patterns constantly. Instead of regenerating code every time:
- 30x faster: Retrieve proven code instead of waiting for generation
- Lower costs: Reduce token usage by reusing cached solutions
- Higher quality: Cached code has been validated and voted on
- Consistent output: Same task = same proven solution
Learn more at raysurfer.com or read the documentation.
安全使用建议
This skill appears coherent: it talks to the Raysurfer API using the single RAYSURFER_API_KEY you provide and implements search/fetch/upload/vote for code snippets. Before installing, consider: 1) Trust the third party (Raysurfer): uploaded code and metadata will be transmitted to their service. 2) Sensitive data risk: any secrets or credentials embedded in code you upload could be leaked — audit or sanitize files before upload. 3) Execution risk: the skill writes retrieved code to disk so your agent or sandbox may execute it — run in an isolated sandbox and review code before execution. 4) Key management: store the API key with least privilege and be prepared to revoke it if needed. If these tradeoffs are acceptable, the skill is internally consistent with its stated purpose.
功能分析
Type: OpenClaw Skill
Name: code-cache
Version: 1.0.0
The skill is classified as suspicious due to its inherent high-risk capabilities, which, while aligned with its stated purpose, present a significant attack surface for misuse. The `code_cache.py` script allows reading arbitrary local files (via `cmd_upload`) and writing arbitrary code received from the Raysurfer API to local files (via `cmd_files`). These operations, coupled with network communication to a third-party API (raysurfer.com), could be exploited through prompt injection against the AI agent to exfiltrate sensitive local files, perform arbitrary file writes, or execute untrusted code. There is no clear evidence of intentional malicious behavior by the skill developer, but the broad permissions and powerful file system interactions warrant a 'suspicious' classification.
能力评估
Purpose & Capability
Name/description, SKILL.md, README, and code all describe a Raysurfer-backed semantic code cache. The only required environment variable is RAYSURFER_API_KEY which directly matches the documented remote API usage.
Instruction Scope
Instructions and CLI operations are scoped to searching, downloading, writing code files to a cache directory, uploading code snippets, and voting — all expected for a caching service. Note: uploads will transmit user code to the external Raysurfer service (explicitly documented). Retrieved snippets are written to disk for execution by the agent/runner, which is expected but is a privacy/safety consideration (see guidance).
Install Mechanism
No install spec is present (instruction-only from the registry point of view) and the repo contains Python CLI code. There are no remote downloads or opaque installers referenced in SKILL.md/README; the code expects a standard 'raysurfer' Python package if used locally.
Credentials
Only one credential is requested (RAYSURFER_API_KEY) which is proportionate to the described remote API usage. However, that key grants the skill network access to the external Raysurfer service and will be used to upload user code — any secrets inside code files could be transmitted.
Persistence & Privilege
always is false and the skill does not request persistent/system-wide privileges or modify other skills' configs. It writes cached files to a user-specified directory (default .code_cache), which is expected behavior.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install code-cache - 安装完成后，直接呼叫该 Skill 的名称或使用
/code-cache触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release: semantic code caching for AI agents via Raysurfer API
元数据
常见问题
Code Cache 是什么？
Semantic code caching for AI agents. Cache, retrieve, and reuse code from prior agent executions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 756 次。
如何安装 Code Cache？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install code-cache」即可一键安装，无需额外配置。
Code Cache 是免费的吗？
是的，Code Cache 完全免费（开源免费），可自由下载、安装和使用。
Code Cache 支持哪些平台？
Code Cache 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Code Cache？
由 ryx2（@ryx2）开发并维护，当前版本 v1.0.0。
推荐 Skills