Author, validate, explain, dry-run, and inspect optional graph.flow.aiwg.io GraphPlaybooks over the AIWG Flow runtime substrate
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add jmagly/aiwg --skill graph-flow-profile --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Graph Flow Profile?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/jmagly-graph-flow-profile)More formats (shields.io, HTML) on the badges page.
---
name: graph-flow-profile
namespace: aiwg
description: Author, validate, explain, dry-run, and inspect optional graph.flow.aiwg.io GraphPlaybooks over the AIWG Flow runtime substrate
triggers:
- graph flow profile
- author a GraphPlaybook
- guarded graph workflow
- inspect graph run routes
platforms: [all]
---
# Graph Flow Profile
Use this skill when a workflow requires conditional routes, guarded feedback,
explicit fan-in reduction, checkpoint/replay lineage, or a mixed-runtime graph
view. Keep ordinary DAGs, local loops, task trees, provider-native workflows,
and durable code in their native patterns when graph-wide state and routing do
not add operator value.
1. Start from a fixture in `agentic/code/addons/graph-pattern/fixtures/`.
2. Keep `apiVersion: graph.flow.aiwg.io/v1` and `kind: GraphPlaybook`.
3. Narrow each node's capabilities and permissions; never inherit authority
from an upstream node.
4. Give cycles a finite guard, fan-in nodes an explicit join/reducer,
side-effecting retries an idempotency key, and HITL nodes complete
approve/deny/timeout routes.
5. Run `aiwg graph validate <file> --format json`, then
`aiwg graph explain <file> --format json` before runtime dispatch.
The validator reuses the Composition Engine's Flow validation. A valid graph
profile is therefore a valid Flow projection; the graph profile is not a
standalone runtime.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
