{
  "markdown": "# opchain\n\n> skills that ship.\n\nA coordinated set of Claude skills covering the full software development\npipeline — discover, spec, design, build, audit, ship, scale. One skill\nper phase. A shared JSON checkpoint protocol carries context across\nsessions and skills, so work resumes where you left off.\n\n**Site & docs:** https://opchain.dev\n\n---\n\n## install\n\n### Claude Code — plugin (recommended)\n\nShips the skills *plus* the hooks that enforce them: a commit gate bound to the\ncode being committed, pipeline state at session start, and a pointer to the next\nskill when one finishes.\n\n```\n/plugin marketplace add asfbay-bit/opchain-skills\n/plugin install opchain\n```\n\n### Claude Code — zip (skills only, no hooks)\n\n```bash\ncurl -L https://opchain.dev/opchain-skills.zip -o opchain-skills.zip\nunzip opchain-skills.zip -d .claude/skills/\nclaude\n> /oc-discover\n```\n\n### Claude.ai / Claude Desktop\n\n1. Download any `SKILL.md` from [`skills/`](./skills)\n2. Open Claude → Settings → Customize → Skills\n3. Upload the file\n4. Start a new conversation and trigger it by name\n\n### Team (check into git)\n\n```bash\ngit add .claude/skills/\ngit commit -m \"chore: add opchain skills\"\ngit push\n```\n\n### Upgrade\n\n```bash\n# .checkpoints/ is a sibling of .claude/ — never touched by this swap\nrm -rf .claude/skills/\ncurl -L https://opchain.dev/opchain-skills.zip -o opchain-skills.zip\nunzip opchain-skills.zip -d .claude/skills/\nrm opchain-skills.zip\n```\n\nVerify the installed version against the published one:\n\n```bash\ncurl -sS https://opchain.dev/api/health | jq .version\n```\n\n---\n\n## skills\n\n| skill | what it does |\n|---|---|\n| `oc-app-architect` | Discover → spec → build, with Generator/Evaluator QA loop |\n| `oc-stack-forge` | Stack advisor across Cloudflare, Vercel, AWS, Supabase, etc. |\n| `oc-ux-engineer` | Design Planner → Generator → Evaluator harness |\n| `oc-dash-forge` | Dashboards and dense-data UIs (spec + React prototype) |\n| `oc-integrations-engineer` | Third-party API integrations (Slack, Stripe, OAuth) |\n| `oc-api-dev` | First-party API design (OpenAPI, GraphQL, SDKs) |\n| `oc-claude-api` | Claude API apps: model routing, prompt caching, tool use |\n| `oc-rag-forge` | RAG systems: vector DBs, embeddings, chunking, retrieval eval |\n| `oc-agent-forge` | Claude Agent SDK apps: topology, tool budgets, harness loops |\n| `oc-prompt-ops` | Prompts as code: versioning, eval datasets, regression detection |\n| `oc-qa-ops` | Test-pyramid design: coverage budgets, contract-test matrix, load plans |\n| `oc-data-ops` | Data pipelines: ingestion, dbt layering, observable data contracts |\n| `oc-signal-forge` | Question → trustworthy metric: instrument, harvest, verify, wire |\n| `oc-code-auditor` | Auditor → Fixer → Verifier; 5-layer pre-deploy sweep |\n| `oc-security-auditor` | Threat modeling, OWASP hardening, attack-surface review |\n| `oc-security-hardening` | Executes the fixes + per-deploy hardening gate (`/oc-harden`) |\n| `oc-compliance-ops` | Control register + audit-ready evidence bundles at deploy time |\n| `oc-bug-check` | Pre-commit QA gate: types, lint, tests, anti-patterns, secrets |\n| `oc-docs-forge` | PR documentation packets, README/changelog/ADR upkeep |\n| `oc-repo-ops` | Repo hygiene + PR readiness gate: catalogs, generated files |\n| `oc-git-ops` | Branches, commits, PRs, sync |\n| `oc-deploy-ops` | Audit gate → staging → production with rollback |\n| `oc-fleet-ops` | Self-managed fleets: IaC, multi-container rollouts, day-2 ops |\n| `oc-modularize-ops` | Live-monolith decomposition with golden-fixture proof |\n| `oc-monitoring-ops` | Post-deploy observability — uptime, errors, alerts |\n| `oc-scale-ops` | Load tests, perf budgets, caching, capacity planning |\n| `oc-migration-ops` | DB / framework / auth / platform migrations |\n| `oc-cost-ops` | LLM cost attribution, budget gates, model-tier routing |\n| `oc-telemetry-ops` | Opt-in local usage metering, anonymized dashboard aggregates |\n| `oc-reverse-spec` | Reverse-engineer existing code into spec docs |\n| `oc-release-ops` | Version bumps, changelogs, release announcements |\n| `oc-orchestrator` | Cross-skill status and routing (`/oc-ops`) |\n| `oc-checkpoint-protocol` | Shared session-persistence schema (bundled in every skill) |\n\nFull descriptions, triggers, and examples: https://opchain.dev/skills\n\n---\n\n## the checkpoint protocol\n\nEvery skill writes a JSON checkpoint to `.checkpoints/` in your project.\nSkills read each other's checkpoints to make informed decisions — context\nflows forward without manual handoffs.\n\n- `oc-deploy-ops` reads `oc-code-auditor` — CRITICAL findings block deploy\n- The build evaluator reads `oc-ux-engineer` — grades frontend against the\n  approved design spec\n- `oc-git-ops` reads `oc-app-architect` — names branches by sprint\n\nSchema lives in\n[`skills/oc-checkpoint-protocol/SKILL.md`](./skills/oc-checkpoint-protocol/SKILL.md).\n\n---\n\n## this repository\n\nThis is a public, force-push snapshot mirror of the skill source. The site,\nbuild system, and internal tooling live in a private upstream repo; only\nthe product (this directory) is published here, refreshed on every change\nto `main` upstream.\n\nSee [CONTRIBUTING.md](./CONTRIBUTING.md) for how issues and PRs flow back\ninto the upstream repo.\n\n---\n\n## license\n\nApache-2.0 — see [LICENSE](./LICENSE) and [NOTICE](./NOTICE). Releases up to and including v1.8.2 were published under MIT.\n",
  "bytes": 5365,
  "sha": "a588029fdc35fad51c0a518f410e513477b2d7bcef1ec52555dd241b136a9d8b",
  "repo_slug": "asfbay-bit/opchain-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_asfbay_bit_opchain_skills_2345ee26/readme"
}