pillumina/ascend-sleuth
昇腾 NPU 训练与推理故障诊断知识库:按症状命中 case、用先验知识与源码分析定位根因,定位后进待审队列、每周升格回库。
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit pillumina/ascend-sleuth/skills ./rig-ascend-sleuth/skills MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit pillumina/ascend-sleuth/skills/ask .claude/skills/ask $ npx degit pillumina/ascend-sleuth/skills/diagnose .claude/skills/diagnose $ npx degit pillumina/ascend-sleuth/skills/doc-standards .claude/skills/doc-standards $ npx degit pillumina/ascend-sleuth/skills/doctor .claude/skills/doctor $ npx degit pillumina/ascend-sleuth/skills/evolve-check .claude/skills/evolve-check $ npx degit pillumina/ascend-sleuth/skills/issue-ingest .claude/skills/issue-ingest $ npx degit pillumina/ascend-sleuth/skills/knowledge-groom .claude/skills/knowledge-groom $ npx degit pillumina/ascend-sleuth/skills/preload-panel .claude/skills/preload-panel $ npx degit pillumina/ascend-sleuth/skills/reference-ingest .claude/skills/reference-ingest $ npx degit pillumina/ascend-sleuth/skills/resume-diagnosis .claude/skills/resume-diagnosis $ npx degit pillumina/ascend-sleuth/skills/self-evolve .claude/skills/self-evolve $ npx degit pillumina/ascend-sleuth/skills/skill-review .claude/skills/skill-review $ npx degit pillumina/ascend-sleuth/skills/to-postmortem .claude/skills/to-postmortem $ npx degit pillumina/ascend-sleuth/skills/to-reference .claude/skills/to-reference
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (14)
Similar rigs
avibebuilder/claude-prime
You've heard Claude Code can do amazing things. Skills, hooks, agents, memory systems — but who has time to figure all that out? Claude Prime sets it up for you in one command.
Skill Collector 2.7k tok · · Q21
yigitkonur/plugin-trigger-dev
Claude Code plugin for Trigger.dev: scenario-aware build/chat-agent/diagnose skills, init/new/audit/ship/doctor commands, a prod-environment guard and an edit tripwire. Includes the official Trigger.dev MCP server.
Pragmatist 5.4k tok · · Q10
Senzing/senzing-claude-plugins
Entity resolution: point Claude at your data, it does the work, and you have results today.
Pragmatist 2.6k tok · · Q15
nyxene/orrery
A working method for software written by AI agents and directed by people: consensus planning, fan-out execution, debt that gets paid, rules earned from real incidents, and guards that fire before every shell call.
Skill Collector 1.5k tok · · Q0