# Send Ultra Agent Stinct to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ultra-agent-stinct",
    "name": "Ultra Agent Stinct",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/grimmjoww/ultra-agent-stinct",
    "canonicalUrl": "https://clawhub.ai/grimmjoww/ultra-agent-stinct",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/ultra-agent-stinct",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ultra-agent-stinct",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "README.md",
      "references/escalation-guide.md",
      "references/git-workflow.md",
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/ultra-agent-stinct"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ultra-agent-stinct",
    "downloadUrl": "https://openagent3.xyz/downloads/ultra-agent-stinct",
    "agentUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/agent.md"
  }
}
```
## Documentation

### Ultra Agent Stinct

Your internal debugging instinct. When something breaks while you're working, this is how you fix it.

### Always Follow These (Any Time You Touch Code)

These rules apply every time, even for quick fixes. No exceptions.

### Safety

Read before edit. Never edit without read first — exact text match required or it fails
write overwrites entirely. Use edit for changes to existing files
Never delete without asking. Prefer safe deletion over rm -rf
Never push without asking. git push only when the user explicitly says to
Never commit without asking. Stage and commit only on request
Backup awareness. Before large refactors, suggest a branch or stash

### Good Practices

Always verify your fix. After every change, re-run the failing command or tests. Never assume it worked
Tell the user what happened. After fixing, briefly explain what broke and what you changed
Read the error first. Don't guess at fixes — read the actual error message, stack trace, or test output before touching code
Minimal changes. Fix the bug, don't refactor the neighborhood. Keep diffs small and focused

### When to Activate Full Workflow

If you hit an error during a task, try a quick fix first while following the rules above. But if you:

Get stuck — your first fix didn't work, same error or new ones
Hit something complex — errors across multiple files, unfamiliar code, architectural issues
Need structure — not sure where the bug is or where to start

Then activate Ultra Agent Stinct — follow the full structured workflows below step by step.

### Debug Workflow

When you encounter an error or something breaks:

1. Reproduce — Run the failing command:

exec command:"<failing command>" workdir:"<project dir>"

2. Read the error — Parse the stack trace. Identify file + line number.

3. Read the code — Read the relevant file(s):

read path:"<file from stack trace>"

4. Trace the cause — Follow the call chain. Read imports, dependencies, config. Check for:

Typos, wrong variable names
Missing imports or dependencies
Type mismatches, null/undefined access
Wrong paths, missing env vars
Logic errors in conditionals

5. Fix — Apply the minimal correct fix:

read path:"<file>"
edit path:"<file>" old:"<exact broken code>" new:"<fixed code>"

6. Verify — Re-run the original failing command. Confirm the fix works.

7. Report — Tell the user what broke and what you fixed (brief). Then continue your original task.

### Writing New Code

When you need to create or modify code as part of a task:

1. Understand the project — Check existing patterns:

exec command:"ls -la" workdir:"<project dir>"

Read package.json, pyproject.toml, Cargo.toml, or equivalent. Match existing style and conventions.

2. Plan first — Before writing, outline what you'll create. Think through structure, dependencies, edge cases.

3. Write — Create the file:

write path:"<new file path>" content:"<complete file content>"

4. Verify — Run it, test it, make sure it actually works before moving on.

### Running Tests

1. Find the test runner:

Node.js: npm test / npx jest / npx vitest
Python: pytest / python -m unittest
Rust: cargo test
Go: go test ./...

2. Run tests:

exec command:"<test command>" workdir:"<project>" timeout:120

3. On failure: Read the failing test, read the source under test, apply Debug Workflow.

4. On success: Report summary and continue.

### Git Integration

Only when the user asks to commit, stage, or check git status.

exec command:"git status" workdir:"<project>"
exec command:"git diff --stat" workdir:"<project>"
exec command:"git add <specific files>" workdir:"<project>"
exec command:"git commit -m '<message>'" workdir:"<project>"

For detailed git workflows, see references/git-workflow.md.

### Spawning Coding Agents (Heavy Tasks)

For large tasks (multi-file refactors, entire features, long builds), spawn a background agent:

exec pty:true workdir:"<project>" background:true command:"claude '<detailed task>'"

Monitor:

process action:list
process action:log sessionId:<id>
process action:poll sessionId:<id>

See references/escalation-guide.md for when to self-handle vs delegate.

### Cross-Platform Quick Reference

TaskmacOS/LinuxWindows (Git Bash)Find filesfind . -name "*.ts" -not -path "*/node_modules/*"SameSearch codegrep -rn "pattern" --include="*.ts" .SameProcess listps aux | grep nodetasklist | findstr nodeKill processkill -9 <PID>taskkill //f //pid <PID>Pythonpython3 (or python)pythonOpen fileopen <file>start <file>

### Context Management

Keep tool calls focused — one task per chain
Don't read files already in your system prompt
For large files, read targeted sections rather than the whole thing
If context is getting heavy, summarize findings before continuing
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: grimmjoww
- Version: 1.2.0
## Source health
- Status: healthy
- Source download looks usable.
- Yavira can redirect you to the upstream package for this source.
- Health scope: source
- Reason: direct_download_ok
- Checked at: 2026-05-07T17:22:31.273Z
- Expires at: 2026-05-14T17:22:31.273Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/ultra-agent-stinct)
- [Send to Agent page](https://openagent3.xyz/skills/ultra-agent-stinct/agent)
- [JSON manifest](https://openagent3.xyz/skills/ultra-agent-stinct/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/ultra-agent-stinct/agent.md)
- [Download page](https://openagent3.xyz/downloads/ultra-agent-stinct)