Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

gh-aw Prompt Surface — measured AI agent skill | DecimalAI

github/gh-aw-prompt-surface

NewSkillScoreMaintained

This repository builds **gh-aw** (GitHub Agentic Workflows), a GitHub CLI extension for writing workflows in markdown and compiling them to GitHub Actions.

by github

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

DevOps & SRE pack

decimalai skills pull github-gh-aw-prompt-surface

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/github-gh-aw-prompt-surface/SKILL.md

Raw file: /s/github-gh-aw-prompt-surface/SKILL.md ↗ · machine-readable summary at /s/github-gh-aw-prompt-surface.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 11h ago

Yes — +45% lift-41% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-52%	0%
case-07	✗→✓	▲ Improved	-50%	0%
case-03	✗→✓	▲ Improved	-30%	0%
case-08	✗→✓	▲ Improved	-55%	0%
case-10	✗→✓	▲ Improved	-70%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

github / gh-aw

SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 41 files · scripts

Skill contents

scripts/

SKILL.md

gh-aw Prompt Surface

This repository builds gh-aw (GitHub Agentic Workflows), a GitHub CLI extension for writing workflows in markdown and compiling them to GitHub Actions.

What this surface does

Converts markdown workflow specs (.md) into compiled lock files (.lock.yml)
Supports multiple AI engines (copilot, claude, codex, custom)
Integrates tools, including GitHub MCP servers and safe-output tooling
Provides CLI commands to compile, run, inspect, and audit workflows

Key concepts

Workflow compilation: edit workflow markdown, then recompile lock files
Engine selection: set engine in frontmatter to control runtime agent behavior
MCP tools: configure GitHub/MCP toolsets in frontmatter for repository operations
Safe outputs: workflow-safe issue/comment output paths and constraints

Representative usage examples

bash
# Compile markdown workflows to lock files
gh aw compile

# Run a workflow manually
gh aw run .github/workflows/daily-skill-optimizer.md

# Inspect MCP server usage in workflows
gh aw mcp list
gh aw mcp inspect daily-skill-optimizer

# Audit a workflow run
gh aw audit 24814681146

Where to learn more in this repo

/AGENTS.md for development/agent workflow conventions
/skills/*/SKILL.md for focused domain guidance (GitHub MCP, docs, errors, etc.)

Want to see if github/gh-aw-prompt-surface would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.