Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Build automated pipelines with reusable components, data flow between nodes, and state management.
Build automated pipelines with reusable components, data flow between nodes, and state management.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
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.
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.
Workflows live in workflows/ with components and flows: workflows/ โโโ index.md # Inventory with tags โโโ components/ โ โโโ connections/ # Auth configs โ โโโ nodes/ # Reusable operations โ โโโ triggers/ # Event sources โโโ flows/{name}/ โโโ flow.md # Definition โโโ config.yaml # Parameters โโโ run.sh # Executable โโโ state/ # Persistent between runs โโโ logs/
TopicFileDirectory layout, naming, formatsstructure.mdData passing between nodesdata-flow.mdCursor, seen set, checkpointstate.mdRetry, rollback, idempotencyerrors.mdConnections, nodes, triggerscomponents.mdCreate, test, update, archivelifecycle.md
jq โ JSON processing yq โ YAML config parsing curl โ HTTP requests flock โ Lock files to prevent concurrent runs Secrets in macOS Keychain (security find-generic-password)
Location: workflows/ in workspace root State: flows/{name}/state/ โ cursor.json, seen.json, checkpoint.json Logs: flows/{name}/logs/ โ JSONL per run Data: flows/{name}/data/ โ intermediate files between nodes
Each node writes output to data/{NN}-{name}.json. Next node reads it. curl ... > data/01-fetch.json jq '...' data/01-fetch.json > data/02-filter.json Breaking this pattern = nodes can't communicate.
Every node in flow.md MUST declare: On error: retry(N) | fail | continue | alert On empty: skip | continue | fail Undefined behavior = unpredictable workflow.
Prevent concurrent runs: LOCKFILE="/tmp/workflow-${NAME}.lock" exec 200>"$LOCKFILE" flock -n 200 || exit 0
FilePurposecursor.json"Where did I leave off?"seen.json"What have I processed?"checkpoint.json"Multi-step recovery"
Before creating new connections/nodes/triggers: ls workflows/components/connections/ ls workflows/components/nodes/ Use existing. Update "Workflows Using This" when adding. Related: For LLM-driven multi-phase processes, see the cycle skill.
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.