Acceptance Orchestrator
State-machine orchestration from issue intake to evidence-verified acceptance, never claiming done without proof.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 10, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · e182064
On a rate-limiting ticket, an unguided run claimed 'Done' with fabricated deploy evidence; following the skill it correctly refused, flagged the unmet issue gate, and returned a structured escalation report instead.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 3/5
What Acceptance Orchestrator does
Drives a coding task end-to-end (intake, issue gate, execution, review loop, deploy-verify, completion gate) and forbids reporting completion without fresh evidence. Use when a task has a clear issue and DoD and should run with minimal human re-intervention, with explicit escalation instead of silent partial completion.
How to install Acceptance Orchestrator
git clone https://github.com/sickn33/antigravity-awesome-skills
cd antigravity-awesome-skills
mkdir -p ~/.claude/skills
cp -r plugins/agentic-awesome-skills-claude/skills/acceptance-orchestrator ~/.claude/skills/acceptance-orchestrator
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Acceptance Orchestrator
-
/acceptance-orchestratorState-machine orchestration from issue intake to evidence-verified acceptance, never claiming done without proof.
It also activates on plain-language prompts like these:
-
Drive this issue from intake to evidence-verified completion -
Run the full review loop and don't mark this done without proof -
Escalate instead of silently leaving this task partially finished
Frequently asked questions
- Is the Acceptance Orchestrator skill free?
- Yes. The skill itself is free from sickn33/antigravity-awesome-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Acceptance Orchestrator work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 10, 2026. Verdict: Tested · Works. On a rate-limiting ticket, an unguided run claimed 'Done' with fabricated deploy evidence; following the skill it correctly refused, flagged the unmet issue gate, and returned a structured escalation report instead.
- What is the Acceptance Orchestrator SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
- How do I install Acceptance Orchestrator?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Acceptance Orchestrator with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.