القائمة
Cache and reuse code from prior AI agent executions via Raysurfer. Search before coding, upload after success.
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/duclm1x1/Dive-Ai --skill raysurferيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
عرض SKILL.md
استنادا إلى تصنيف SOC المهني
| name | raysurfer |
| description | Cache and reuse code from prior AI agent executions via Raysurfer. Search before coding, upload after success. |
| argument-hint | [search query or "upload"] |
| allowed-tools | ["Bash","Read","Write","Edit","Grep","Glob"] |
You have access to Raysurfer, a code caching system that stores and retrieves code from prior AI agent executions. Always check the cache before writing new code and upload successful results afterward.
https://api.raysurfer.comRAYSURFER_API_KEY environment variableContent-Type: application/jsonFollow this sequence for every coding task:
Before writing any code, search for existing cached solutions.
To also include community public snippets (crawled from GitHub), add the X-Raysurfer-Public-Snips: true header.
curl -s -X POST https://api.raysurfer.com/api/retrieve/search \
-H "Authorization: Bearer $RAYSURFER_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Raysurfer-Public-Snips: true" \
-d
The response contains:
{
"matches": [
{
"code_block": {
"id": "uuid",
"name": "descriptive name",
"description": "what this code does",
"source": "the actual code content",
"language": "python"
},
"combined_score": 0.85,
"filename": "suggested_filename.py",
"thumbs_up": 12,
"thumbs_down": 1
}
],
"total_found": 3,
"cache_hit": true
}
Decision logic:
total_found > 0 and the top match has combined_score >= 0.7 and a favorable vote ratio (thumbs_up > thumbs_down), use the cached code.When a good cache hit is found:
source field from the best matching code_block.When no suitable cache hit exists:
After using cached code, report whether it worked:
curl -s -X POST https://api.raysurfer.com/api/store/cache-usage \
-H "Authorization: Bearer $RAYSURFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"code_block_id": "<id from the match>", "code_block_name": "<name from the match>", "code_block_description": "<description from the match>", "succeeded": true, "task": "<the task description>"}'
Set succeeded to true if the code ran correctly, false if it failed or needed significant changes.
After successfully generating and running new code (cache miss), upload it for future reuse:
curl -s -X POST https://api.raysurfer.com/api/store/execution-result \
-H "Authorization: Bearer $RAYSURFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"task": "<describe what this code does>",
"file_written": {"path": "relative/path/to/file.py", "content": "<full file content>"},
"succeeded": true
}'
Only upload code that executed successfully. AI voting is enabled by default.
/raysurfer parse CSV and generate chart), run Step 1 with that query as the task.upload (e.g., /raysurfer upload), run Step 4 for the most recently generated code in the conversation.When $ARGUMENTS is provided, use it as: $ARGUMENTS
Ready-to-run scripts are in this skill's directory. Requires RAYSURFER_API_KEY to be set.
python search.py "Parse a CSV and plot a chart"
bun search.ts "Parse a CSV and plot a chart"
bash search.sh "Parse a CSV and plot a chart"
python upload.py "Generate a bar chart" chart.py
bun upload.ts "Generate a bar chart" chart.py
bash upload.sh "Generate a bar chart" chart.py
RAYSURFER_API_KEY is set before making API calls. If unset, inform the user and skip cache operations.task strings that capture what the code does, not how it does it (e.g., "Parse CSV file and generate a bar chart with matplotlib" rather than "run pandas read_csv and plt.bar").| Action | Endpoint | Method |
|---|---|---|
| Search cache | /api/retrieve/search | POST |
| Upload code | /api/store/execution-result | POST |
| Vote on code | /api/store/cache-usage | POST |
See references/api-reference.md for full request and response schemas.