一键导入
apastra-setup-ci
Upgrade from local-first evaluation to automated GitHub Actions CI. Installs workflows for PR gating, release promotion, and auto-merge.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Upgrade from local-first evaluation to automated GitHub Actions CI. Installs workflows for PR gating, release promotion, and auto-merge.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | apastra-setup-ci |
| description | Upgrade from local-first evaluation to automated GitHub Actions CI. Installs workflows for PR gating, release promotion, and auto-merge. |
Upgrade your local-first PromptOps workflow with GitHub Actions. This adds PR gating, release automation, and autonomous promotion tracking to your repository.
Apastra is designed to be CI optional. You can start local-first (using your IDE agent as the harness) and upgrade to CI any time just by dropping these workflows into your repository. The core file-based protocol never changes.
Use this skill when you want to:
When the user asks to "set up apastra CI" or "upgrade to CI", do the following:
This skill includes pre-built GitHub Actions workflows in its templates/.github/workflows/ directory.
Copy these directly into the user's project:
mkdir -p .github/workflows
cp -r .agents/skills/apastra-setup-ci/templates/.github/workflows/* .github/workflows/
Explain what these workflows do for the project:
regression-gate.yml
auto-merge.yml
regression-gate), it automatically merges the PR.promote.yml
derived-index/promotions/ linking the verified digest to the prod channel.deliver.yml
immutable-release.yml
v1.2.0)Advise the user to go to their GitHub repository settings:
promptops-regression-gate job to the required list.Now no one (not even an autonomous agent) can merge a prompt change that drops quality below the established baseline.
Remind the user that the core workflow remains the same:
promptops/prompts/promptops/datasets/npx skills add BintzGavin/apastra/skills/evalYou (the agent editing the user's code) do not need to rewrite or configure complex cloud integrations. The GitHub Actions workflows handle the external compute. Just ensure the files exist in .github/workflows/.
PromptOps skills for versioning, evaluating, tracing, and shipping AI prompts as disciplined software assets. Agent-as-harness — your IDE agent runs evals, compares baselines, surfaces trace evidence, and gates quality.
Quick setup guide for apastra PromptOps. Create your first prompt spec, dataset, evaluator, and suite in 5 minutes.
Run prompt evaluations using your IDE agent as the harness. Load suites, execute test cases, score results, and compare against baselines.
Generate new prompt specs, datasets, evaluators, and suites from templates. Creates correctly-formatted files that pass schema validation.
Inspect agent traces, hook events, tool-call transcripts, and run artifacts; turn them into PromptOps evidence, eval cases, and artifact references.
Interactive PromptOps eval design — what behavior to pin down, cases, scoring, thresholds, and outcome/step/trace evidence. Deep link to Writing evals once per session; pair with scaffold + apastra-eval.