# Send Pipeline 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. 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. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
"schemaVersion": "1.0",
"item": {
"slug": "solo-pipeline",
"name": "Pipeline",
"source": "tencent",
"type": "skill",
"category": "开发工具",
"sourceUrl": "https://clawhub.ai/fortunto2/solo-pipeline",
"canonicalUrl": "https://clawhub.ai/fortunto2/solo-pipeline",
"targetPlatform": "OpenClaw"
},
"install": {
"downloadUrl": "/downloads/solo-pipeline",
"sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=solo-pipeline",
"sourcePlatform": "tencent",
"targetPlatform": "OpenClaw",
"packageFormat": "ZIP package",
"primaryDoc": "SKILL.md",
"includedAssets": [
"SKILL.md"
],
"downloadMode": "redirect",
"sourceHealth": {
"source": "tencent",
"slug": "solo-pipeline",
"status": "healthy",
"reason": "direct_download_ok",
"recommendedAction": "download",
"checkedAt": "2026-05-07T03:23:06.937Z",
"expiresAt": "2026-05-14T03:23:06.937Z",
"httpStatus": 200,
"finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=solo-pipeline",
"contentType": "application/zip",
"probeMethod": "head",
"details": {
"probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=solo-pipeline",
"contentDisposition": "attachment; filename=\"solo-pipeline-1.4.0.zip\"",
"redirectLocation": null,
"bodySnippet": null,
"slug": "solo-pipeline"
},
"scope": "item",
"summary": "Item download looks usable.",
"detail": "Yavira can redirect you to the upstream package for this item.",
"primaryActionLabel": "Download for OpenClaw",
"primaryActionHref": "/downloads/solo-pipeline"
},
"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/solo-pipeline",
"downloadUrl": "https://openagent3.xyz/downloads/solo-pipeline",
"agentUrl": "https://openagent3.xyz/skills/solo-pipeline/agent",
"manifestUrl": "https://openagent3.xyz/skills/solo-pipeline/agent.json",
"briefUrl": "https://openagent3.xyz/skills/solo-pipeline/agent.md"
}
}
```
## Documentation
### /pipeline
Launch an automated multi-skill pipeline. The Stop hook chains skills automatically — no manual invocation needed between stages.
### Research Pipeline
/pipeline research "AI therapist app"
Chains: /research -> /validate
Produces: research.md -> prd.md
### Dev Pipeline
/pipeline dev "project-name" "stack"
/pipeline dev "project-name" "stack" --feature "user onboarding"
Chains: /scaffold -> /setup -> /plan -> /build
Produces: full project with workflow, plan, and implementation
### 1. Parse Arguments
Extract from $ARGUMENTS:
Pipeline type: first word (research or dev)
Remaining args: passed to the launcher script
If no arguments or unclear, ask:
Which pipeline do you want to run?
1. Research Pipeline — /research → /validate (idea to PRD)
2. Dev Pipeline — /scaffold → /setup → /plan → /build (PRD to running code)
### 2. Confirm with User
Show what will happen:
Pipeline: {type}
Stages: {stage1} → {stage2} → ...
Idea/Project: {name}
This will run multiple skills automatically. Continue?
Ask via AskUserQuestion.
### 3. Start First Stage
Run the first skill in the pipeline directly:
For research pipeline: Run /research "idea name"
For dev pipeline: Run /scaffold project-name stack
The Stop hook (if configured) will handle subsequent stages automatically.
Without a Stop hook, manually invoke each skill in sequence.
### 3b. Launcher Scripts (optional, Claude Code plugin only)
If you have the solo-factory plugin installed, launcher scripts provide tmux dashboard and logging:
# Only available with Claude Code plugin — skip if not installed
solo-research.sh "idea name" [--project name]
solo-dev.sh "project-name" "stack" [--feature "desc"]
Pass --no-dashboard when running from within a skill context.
### 5. Pipeline Completion
When all stages are done, output:
The Stop hook checks for this signal and cleans up the state file.
### State File
Location: .solo/pipelines/solo-pipeline-{project}.local.md (project-local) or ~/.solo/pipelines/solo-pipeline-{project}.local.md (global fallback)
Log file: .solo/pipelines/solo-pipeline-{project}.log
Format: YAML frontmatter with stages list, project_root, and log_file fields.
The Stop hook reads this file on every session exit attempt.
To cancel a pipeline manually: delete the state file solo-pipeline-{project}.local.md
### tmux Dashboard (terminal use)
When launched from terminal (without --no-dashboard), a tmux dashboard opens automatically with:
Pane 0: work area
Pane 1: tail -f on log file
Pane 2: live status display (refreshes every 2s)
### Manual Monitoring
Monitor pipeline progress with standard tools:
# Watch log file
tail -f .solo/pipelines/solo-pipeline-.log
# Check pipeline state
# Auto-refresh
watch -n2 -c solo-pipeline-status.sh
Otherwise, use standard tools:
# Log tail
tail -f .solo/pipelines/solo-pipeline-.log
# Check state file
cat .solo/pipelines/solo-pipeline-.local.md
### Session Reuse
Re-running a pipeline reuses any existing state — completed stages are skipped automatically.
No need to close/recreate — just run the same command again
### Log Format
[22:30:15] START | my-app | stages: research -> validate | max: 5
[22:30:16] STAGE | iter 1/5 | stage 1/2: research
[22:30:16] INVOKE | /research "AI therapist app"
[22:35:42] CHECK | research | .../research.md -> FOUND
[22:35:42] STAGE | iter 2/5 | stage 2/2: validate
[22:35:42] INVOKE | /validate "AI therapist app"
[22:40:10] CHECK | validate | .../prd.md -> FOUND
[22:40:10] DONE | All stages complete! Promise detected.
[22:40:10] FINISH | Duration: 10m
### Critical Rules
Always confirm before starting a pipeline.
Don't skip stages — the hook handles progression.
Cancel = delete state file — tell users this if they want to stop.
Max iterations prevent infinite loops (default 5 for research, 15 for dev).
Use --no-dashboard when running from within Claude Code skill context.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: fortunto2
- Version: 1.4.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-07T03:23:06.937Z
- Expires at: 2026-05-14T03:23:06.937Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/solo-pipeline)
- [Send to Agent page](https://openagent3.xyz/skills/solo-pipeline/agent)
- [JSON manifest](https://openagent3.xyz/skills/solo-pipeline/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/solo-pipeline/agent.md)
- [Download page](https://openagent3.xyz/downloads/solo-pipeline)