Skill comparison

Compare agent skills before installing.

Put high-signal skills side by side and inspect quality, adoption, freshness, install readiness, use-case fit, and warnings in one place.

Comparing 1 skill

Use this as a shortlist, then open the skill detail page before adopting.

Add more skills

Decision summary

agent-launcher-orchestrator is the strongest overall pick here because it has a 100/100 readiness score and fits Workflow automation.

Strongest overall

agent-launcher-orchestrator

Use this as a leading candidate, then validate the README and install path in your own agent stack.

Fastest prototype

agent-launcher-orchestrator

Best first install candidate based on install readiness and adoption.

Freshest repo

agent-launcher-orchestrator

Most recent maintenance signal among this shortlist.

Signal	agent-launcher-orchestrator Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CM
Quality	95/100 Excellent
Decision verdict	100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack.
Adoption	25K stars Verified outcomes are shown on each skill page
Freshness	Aug 27, 2026
Use-case fit	Workflow automation RAG and knowledge Research agents
Workflow fit	Content growth agent Research report agent
Platform hints	Claude Code, OpenAI Agents, Cursor
Warnings	The underlying Python scripts (goal_router.py, loop_compiler.py, goal_state.py) are not included in the submission, so their behavior cannot be fully audited; ensure they do not execute untrusted content from goal.json or make unintended network calls. · No OpenAgentSkill engagement data yet

Signal

agent-launcher-orchestrator

Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CM

Quality

95/100

Excellent

Decision verdict

100/100

Production-ready

Use this as a leading candidate, then validate the README and install path in your own agent stack.

Adoption

25K stars

Verified outcomes are shown on each skill page

Freshness

Aug 27, 2026

Use-case fit

Workflow automation RAG and knowledge Research agents

Workflow fit

Content growth agent Research report agent

Platform hints

Claude Code, OpenAI Agents, Cursor

Warnings

The underlying Python scripts (goal_router.py, loop_compiler.py, goal_state.py) are not included in the submission, so their behavior cannot be fully audited; ensure they do not execute untrusted content from goal.json or make unintended network calls. · No OpenAgentSkill engagement data yet