Menu
Use when creating, compiling, validating, running, or debugging GitHub Agentic Workflows with the gh-aw CLI.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | gh-aw |
| description | Use when creating, compiling, validating, running, or debugging GitHub Agentic Workflows with the gh-aw CLI. |
Use this skill whenever work touches GitHub Agentic Workflows in .github/workflows/, their generated .lock.yml files, or the gh aw command line workflow around them.
.md workflows into .lock.yml filesgh aw is installed and ready.github/workflows/*.md as the source of truth and .github/workflows/*.lock.yml as generated output.gh aw compile --validate after any frontmatter change or when you add a new workflow.safe-outputs: for issue, PR, or comment writes.daily on weekdays when the workflow is meant to run regularly..gitattributes marks .lock.yml files as generated with linguist-generated=true merge=ours.gh aw is missing, install it with an immutable script URL such as curl -fsSL https://raw.githubusercontent.com/github/gh-aw/13ac7dee59ec5127393ec22dc3f4d0f6987a3842/install-gh-aw.sh -o /tmp/install-gh-aw.sh && bash /tmp/install-gh-aw.sh v0.67.1 && rm -f /tmp/install-gh-aw.sh, then verify with gh aw version.gh aw new <workflow-id> or write .github/workflows/<workflow-id>.md directly.gh aw validate <workflow-id> while iterating.gh aw compile <workflow-id> --validate before committing.gh aw run <workflow-id> or gh aw trial <workflow-id> when you need an execution check.gh aw status, gh aw logs, and gh aw audit to troubleshoot runtime behavior.gh aw addgh aw add-wizardgh aw auditgh aw checksgh aw compilegh aw completiongh aw disablegh aw domainsgh aw enablegh aw fixgh aw hash-frontmattergh aw healthgh aw initgh aw listgh aw logsgh aw mcpgh aw mcp-servergh aw newgh aw prgh aw projectgh aw removegh aw rungh aw secretsgh aw statusgh aw trialgh aw updategh aw upgradegh aw validategh aw version{
"features": {
"ghcr.io/devcontainers/features/github-cli:1": {}
},
"postCreateCommand": "curl -fsSL https://raw.githubusercontent.com/github/gh-aw/13ac7dee59ec5127393ec22dc3f4d0f6987a3842/install-gh-aw.sh -o /tmp/install-gh-aw.sh && bash /tmp/install-gh-aw.sh v0.67.1 && rm -f /tmp/install-gh-aw.sh"
}
- name: Install gh-aw extension
run: curl -fsSL https://raw.githubusercontent.com/github/gh-aw/13ac7dee59ec5127393ec22dc3f4d0f6987a3842/install-gh-aw.sh -o /tmp/install-gh-aw.sh && bash /tmp/install-gh-aw.sh v0.67.1 && rm -f /tmp/install-gh-aw.sh
Create, load, merge, and distribute persistent artifact plugin bundles for activation steering. Use this skill when the user wants to manage steering artifacts, create distributable plugin packs, load model bundles, merge multiple plugins, write new artifact directories, or work with the plugin directory tree. Also trigger when the user mentions artifact plugins, plugin bundles, plugin manifests, controllers.json, activations.json, or the artifacts/ directory layout.
Define, discover, and manage cognitive feature specifications and steering vectors for LLM activation steering. Use this skill when the user wants to create feature specs, define extraction examples with positive/negative labels, set evaluation criteria, discover feature vectors from specs, persist discovered vectors, work with the standard feature catalog, or manage the feature lifecycle. Also trigger when the user mentions feature extraction, feature catalog, feature specs, cognitive features, or interaction features.
Build and query Neo4j-backed reasoning trajectory graphs for the hybrid meta-cognition agent. Use this skill when the user wants to persist task plans, subgoals, constraints, run states, and verifier outcomes in a Neo4j graph, retrieve evidence paths with PathRAG, or store drift-correction records. Also trigger when the user mentions Neo4j, GraphRAG, PathRAG, reasoning trajectories, graph store, evidence paths, or task plan graphs — even if they don't say "graphrag" explicitly.
Build and run a hybrid planner/retriever/steered-executor/verifier meta-cognition agent loop with persistent steering memory. Use this skill when the user wants to create an agent that plans tasks, retrieves context, applies activation steering, verifies results, and writes back to memory. Also use when the user mentions HybridMetaCognitionAgent, SteeredExecutor, planner/verifier loops, steering controllers, agent runs, or activation traces — even if they don't say "hybrid agent" explicitly.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Run activation-steering feature discovery for a Hugging Face model. Use this skill whenever the user says /steering, wants to steer a model, extract a cognitive feature, generate steering vectors, run feature discovery, or produce steering artifacts. Specify a model (default: gpt2) and an optional feature name. If a feature is supplied, generate inputs, expected outputs, then run an extraction pass and output artifacts. If no feature is supplied, auto-pick one that hasn't already been extracted. If no test data is supplied, generate synthetic examples; otherwise use the user's data and fill in whatever's missing.