skills/pipeline/SKILL.md
--- name: pipeline description: Declarative multi-stage pipeline — Stage 1: lint → Stage 2: test → Stage 3: build → Stage 4: deploy, each stage gates the next --- # Pipeline Declarative multi-stage pipeline with hard gates between stages. Each stage must pass before the next begins. Stages are: lint → test → build → deploy. Failed stages produce actionable diagnostics, not silent failures. ## When to Use - You need a reliable, repeatable delivery pipeline - Changes must pass quality gates be
npx skillsauth add Thomashighbaugh/opencode skills/pipelineInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Declarative multi-stage pipeline with hard gates between stages. Each stage must pass before the next begins. Stages are: lint → test → build → deploy. Failed stages produce actionable diagnostics, not silent failures.
Do not use when:
ralph or tdd instead/ideation insteadplan-execute insteadultrawork insteadRun all linting and formatting checks:
@executor to auto-fix fixable issuesGate rule: Lint must pass with zero errors. Warnings are acceptable but should be noted.
Run the full test suite:
@debugger to diagnose and fix failuresGate rule: All tests must pass. Coverage thresholds should be checked but are advisory (not a hard gate unless configured).
Run the production build:
@debugger to diagnoseGate rule: Build must succeed with zero errors. Warnings should be noted but do not block.
Deploy the built artifacts:
Gate rule: Deploy only runs if Stages 1-3 all passed. If deploy fails, roll back if possible and report.
When a stage fails:
@executor for lint fixes, @debugger for test/build failures)Track pipeline progress in .opencode/state/orchestration/pipeline/{slug}-pipeline.json:
{
"stages": {
"lint": { "status": "passed", "output": "...", "duration": 12 },
"test": { "status": "passed", "output": "...", "duration": 45 },
"build": { "status": "failed", "output": "...", "duration": 30, "attempts": 2 },
"deploy": { "status": "blocked", "output": null, "duration": null }
},
"started_at": "2026-06-20T10:00:00Z",
"completed_at": null
}
Multi-stage pipeline with hard gates.
tools
Create valid, type-safe TypeScript tools for OpenCode — generates correct boilerplate, typed interfaces, and handler stubs. Use when building new tools for global config or per-project .opencode/tools/.
testing
Explore multiple solution branches in parallel, evaluate each, and recommend the best path. Use when the user explicitly invokes /ideation tree-of-thoughts or asks for "tree of thought" / "branching exploration".
testing
Run multiple independent reasoning passes and find consensus. Use when the decision is critically important, the stakes are high, or the user explicitly requests "run it multiple times" / "check consistency" / "self-consistency".
testing
Optimization by PROmpting — generate candidate prompt variations, test each against a benchmark, and report the best performer. Use when the user invokes /ideation opro or asks for "prompt optimization" / "OPRO".