graph
Graph engineering for parallel task execution: convert a task, PRD, SPEC, or issue set into a dependency graph (DAG), layer it into supersteps, then implement each independent node concurrently with subagents — each node runs /goal → /review-it → /ship-it in an isolated git worktree, with a fan-in barrier between waves. Triggers on: graph, graph engineering, build a graph, task graph, dependency graph, DAG, parallel implement, 并发实现, 并行实现, 任务图, 把任务变成图, fan-out fan-in, superstep, dynamic workflow.
npx skills add smallnest/goal-workflow --skill graph --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# graph — Task/PRD to Parallel Execution Graph Turn a task (or PRD / SPEC / issue set) into a **directed acyclic graph** of work units, layer it into **supersteps (waves)**, and implement each wave's independent nodes **concurrently** using subagents. Each node runs the full `/goal → /review-it → /ship-it` pipeline inside its **own git worktree**, so parallel nodes never clobber each other's working tree. Between waves, a **fan-in barrier** merges results and re-plans the next wave. This is the parallel sibling of `/loop-it`. `/loop-it` is strictly sequential (one worktree, one issue at a time). `/graph` fans out every independent node in a wave at once. --- ## Mental Model (borrowed from LangGraph / graph engineering) | Concept | Here | |---------|------| | **Node** | One implementable unit of work (an issue / subtask) | | **Edge** | A dependency: `B depends on A` → edge `A → B` | | **Superstep / wave** | A set of nodes whose deps are all satisfied — run concurrently | | **Fan-out** | Dispatch one subagent per node in the current wave | | **Fan-in (barrier)** | Wait for **all** nodes in the wave before starting the next | | **State channel** | `.graph_state` — shared checkpoint, r
- Mental Model (borrowed from LangGraph / graph engineering)
- Overview
- Step 1: Locate & Decompose Input
- Step 2: Build the DAG & Validate
- Step 3: Topological Layering into Waves
- Step 4: Pre-flight Checks
- Step 5: Execute Wave by Wave (fan-out → fan-in)
- 5a. FAN-OUT — one subagent per node, in parallel
- 5b. FAN-IN — barrier, integrate, re-plan
- State File: .graphstate (+ live tracker graph.html)
- Safety Guards
- Common Mistakes
- Relationship to Other Skills
git rev-parse --is-inside-work-tree # in a repo?
git status --porcelain # clean tree? (dirty → stash/abort)
git branch --show-current # on main/master?
git ls-remote --heads origin # remote reachable?
gh auth status # if shipping to GitHub
cat > .graph_state <<'JSON'
grep -qxF '.graph_state' .gitignore || printf '.graph_state\ngraph.html\n' >> .gitignore
python3 skills/graph/scripts/render_graph_html.py .graph_state graph.html
The orchestrator creates a worktree per node BEFORE dispatching:
git worktree add -b feat/node-{N}-{slug} ../.graph-worktrees/node-{N} mainWhat does the graph skill do?
Graph engineering for parallel task execution: convert a task, PRD, SPEC, or issue set into a dependency graph (DAG), layer it into supersteps, then implement each independent node concurrently with subagents — each node runs /goal → /review-it → /ship-it in an isolated git worktree, with a fan-in barrier between waves. Triggers on: graph, graph engineering, build a graph, task graph, dependency graph, DAG, parallel implement, 并发实现, 并行实现, 任务图, 把任务变成图, fan-out fan-in, superstep, dynamic workflow.
How do I install it?
Run `npx skills add smallnest/goal-workflow --skill graph --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From smallnest/goal-workflow, a repository with 199 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.