메뉴
Sets up and maintains CI/CD pipelines for the Gyst project using GitHub Actions. Use when the user mentions "CI," "CD," "pipeline," "deploy," "actions," "workflow," "release," or "publish." Also use when creating or modifying .github/workflows/ files.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Tests Gyst compatibility with self-hosted LLMs running through Ollama, vLLM, and OpenCode. Use when the user mentions "self-hosted," "local LLM," "Ollama," "vLLM," "OpenCode," "private," or "on-premise." Also use when testing MCP compatibility across different clients.
Analyzes current algorithms in Gyst and proposes specific improvements based on real eval data. Use when the user says "improve," "optimize," "better search," "fix retrieval," "algorithm," "brainstorm," or when eval metrics show degradation. Also use after running retrieval-eval.ts.
Enforces code uniformity across the entire Gyst codebase. This skill activates on EVERY file edit in src/. It checks patterns, naming, imports, error handling, logging, and database access. Use when writing, reviewing, or modifying any TypeScript file. Auto-activate always.
Detects bugs, logic errors, and unsafe patterns in TypeScript code. Use when writing new functions, reviewing code, fixing errors, or when the user says "check for bugs" or "review this." Auto-activate when editing files in src/.
Enforces consistent code patterns across the Gyst codebase. Use when writing new code, reviewing changes, or when the user mentions "consistency," "uniformity," "patterns," or "refactor." Auto-activate on any src/**/*.ts file.
Collects git logs, error messages, conventions, and project metadata from local repositories to build Gyst evaluation datasets. Use when the user says "collect data," "build test fixtures," "get git logs," "seed the database," "gather project data," or "build eval dataset." Also use when setting up the retrieval evaluation harness.
| name | cicd-pipeline |
| description | Sets up and maintains CI/CD pipelines for the Gyst project using GitHub Actions. Use when the user mentions "CI," "CD," "pipeline," "deploy," "actions," "workflow," "release," or "publish." Also use when creating or modifying .github/workflows/ files. |
| allowed-tools | Bash, Read, Write, Glob |
| paths | .github/**/*.yml, .github/**/*.yaml |
This project uses GitHub Actions for CI/CD. All workflows live in .github/workflows/.
Three workflows, triggered by different events:
ci.yml — Runs on every push and PRJobs: lint, test, security, eval (sequential, each depends on the previous)
bun run lint (tsc --noEmit)bun test + upload test-results artifactAKIA, sk-, -----BEGIN.*KEY, xoxb-, xapp-, gho_) in src/, grep for console.log in src/, run tests/compiler/security.test.tsbun run eval, check MRR@5 ≥ 0.5 threshold, upload tests/eval/results.json as artifactrelease.yml — Runs on version tags v*softprops/action-gh-release@v2NPM_TOKEN is configured)eval-regression.yml — Weekly retrieval quality check0 6 * * 1 (Monday 6am UTC) + workflow_dispatchscripts/compare-eval.tsactions/github-script@v7Set in GitHub repo Settings → Secrets:
NPM_TOKEN — for npm publish (optional, not wired yet)No other secrets needed for CI — all tests run locally.
tsc --noEmit)bun test)console.log in src/ (grep scan)any types in src/ (tsc strict mode handles this){
"scripts": {
"lint": "tsc --noEmit",
"test": "bun test",
"build": "bun build src/mcp/server.ts --outdir dist --target node",
"eval": "bun run tests/eval/retrieval-eval.ts",
"eval:tune": "bun run tests/eval/tune-weights.ts",
"calibrate": "bun run scripts/calibrate-confidence.ts"
}
}
# 1. Update version in package.json
# 2. Commit
git add package.json && git commit -m "release: v0.1.0"
# 3. Tag
git tag v0.1.0
# 4. Push
git push origin main --tags
# GitHub Actions handles the rest: tests → build → release
ci.yml for the standard setup-bun + install pattern — match itoven-sh/setup-bun@v2 with bun-version: latestactions/checkout@v4bun install --frozen-lockfile in CI