all publishers

onsager-ai

@onsager-ai source repo

26 published skills

  1. ▌
    Verification Authoring 2 · onsager-ai
    Author Duhem Verification Definitions (criteria + checks YAML) that verify your product's features. Use when asked to "write a verification", "spec acceptance criteria", "author checks", "verify this feature", "translate criteria to checks", "write criteria", or "draft a Verification Definition" against a product you verify with Duhem. Enforces Duhem's Holistic Verification Principle (no mocks of the web), the criteria-vs-checks separation (criteria stable, checks derivative), and the mechanical-judgment rule (no LLM-in-the-loop verdicts).
    7 repo stars
  2. ▌
    Onsager Dogfood · onsager-ai
    Dogfood Duhem against the products it verifies (Onsager, Chreode, Crawlab) — Duhem-as-tool with co-located `.duhem/` VDs. Use when authoring or maintaining a product's Verification Definitions, when wiring a product self-gate (Mode A) or Duhem's drift-monitoring lane (Mode B), when triaging a verdict that fired on a product PR, or when you're unsure which side of the Duhem/product seam owns a change. Covers the cross-repo discipline (which spec lives where, which PR opens where), the trust model (mechanical judgment + a self-verified Duhem contract + optional CODEOWNERS/hub — not hoarded checks), and `docs/duhem-spec.md` §10.1 Pattern D / Appendix D / §14. Triggers include "dogfood on Onsager", "dogfood on Chreode", "verify against a product", "product PR check", "drift monitoring", "co-locate VDs", "cross-repo spec", "which repo owns this", "Duhem/product boundary".
    7 repo stars
  3. ▌
    Duhem Dev Process · onsager-ai
    The end-to-end spec-issue-driven dev loop for Duhem — spec → branch → implement → PR → merge → closure. Use when asked "how do I start work", "what's the process", "SDD loop", "spec-driven development", "how do we ship a change on Duhem", "from scratch what do I do", or when you're about to begin a non-trivial change on the Duhem repo and haven't yet decided how to split spec/PR. Delegates to `issue-spec` (spec writing), the global `pre-push` (pre-push checks) and `pr-lifecycle` (post-push) skills, `verification-authoring` (authoring Verification Definitions for the platform itself), and `onsager-dogfood` (running Duhem against the Onsager repo). This skill carries Duhem's overlay for `pre-push` / `pr-lifecycle` — the check gate, merge-collision patterns, and CI-failure table.
    7 repo stars
  4. ▌
    Verification Authoring · onsager-ai
    Author Duhem Verification Definitions (criteria + checks YAML) for features under verification. Use when asked to "write a verification", "spec acceptance criteria", "author checks", "verify this feature", "translate criteria to checks", "write criteria", "draft a Verification Definition", or when a Duhem product-surface spec needs a worked example, or when adding a Verification Definition to dogfood a feature on onsager-ai/onsager. Enforces Duhem's Holistic Verification Principle (no mocks of the web), the criteria-vs-checks separation (criteria stable, checks derivative), and the mechanical-judgment rule (no LLM-in-the-loop verdicts).
    7 repo stars
  5. ▌
    Onsager Ftue Chat · onsager-ai
    Design a first workflow draft from the workspace-less Onsager `/chat` entry — for users who haven't created a workspace, installed the GitHub App, or picked a repo yet. Triggers include "I'm new to Onsager", "show me what Onsager can do", "help me get started", "design my first workflow", "what's a workflow", "sketch a workflow for me", "draft a workflow", "can you propose a workflow", "set up an automation but I don't have a workspace yet". Drafts live client-side in the dashboard until the binding step promotes them into a real spine workflow; this skill never asks for workspace_id / install_id / repo. For workspace-scoped design (the user already has somewhere to land the workflow), hand off to `onsager-design-workflow`.
    7 repo stars
  6. ▌
    Onsager Triage Run · onsager-ai
    Diagnose why an Onsager run failed, got stuck, or parked unexpectedly — pull the artifact summary, fetch agent-session logs, surface log pointers from the v1 stub, and (when there's no path forward) cancel the run. Triggers include "the run failed", "diagnose this", "why did it fail", "this workflow is stuck", "the artifact is parked", "look at the logs for run X", "cancel run X". This skill does the *reasoning* client-side because `propose_remediation` is a v1 stub that only returns pointers — server-side AI reasoning is a follow-up to ADR 0007.
    7 repo stars
  7. ▌
    Onsager Run Workflow · onsager-ai
    Fire an Onsager workflow's manual trigger to start a new run and surface the resulting artifact. Triggers include "run this workflow", "execute the pipeline", "trigger a run", "kick off the digest workflow", "fire the backfill once", "run the manual workflow named go". Allowed tools cover the manual-trigger fire, recent-runs lookup (to discover the artifact the runtime materialises asynchronously), and an initial inspection. Deep diagnosis lives in `onsager-triage-run`.
    7 repo stars
  8. ▌
    Onsager Design Workflow · onsager-ai
    Design a new Onsager workflow — pick a trigger, chain ordered stages, and create the workflow inactive via the portal MCP server. Triggers include "design a workflow", "create an automation", "build a pipeline", "set up a workflow that fires on issue webhooks", "schedule a workflow to run every morning", "deactivate this workflow". Allowed tools cover the full create/list/edit/schedule surface; activation runs through the REST PATCH endpoint, not MCP.
    7 repo stars
  9. ▌
    Onsager Explore Artifacts · onsager-ai
    Browse the artifacts an Onsager workflow has produced — list recent runs for a workflow, then drill into a specific artifact's metadata and current state. Triggers include "show me the artifacts", "what did this run produce", "list recent runs of the workflow", "what artifacts has this workflow created", "show me artifact `art_…`", "what's the state of run `art_…`". Read-only — no mutations. For diagnosis when something failed, use `onsager-triage-run`.
    7 repo stars
  10. ▌
    Railway · onsager-ai bundle
    Debug, develop, and operate apps hosted on Railway (railway.com) from the CLI — list projects/services, tail and filter build/deploy/HTTP logs, read metrics, inspect and set variables, deploy from the current directory, redeploy / restart / roll back, run local commands with the service's env, SSH into containers, and open a DB shell. Authenticates via the `RAILWAY_TOKEN` environment variable (account token, or project-scoped token). Optional bundled scripts (`scripts/preflight.sh`, `scripts/debug.sh`, `scripts/smoke.sh`) are Onsager-specific wrappers — other repos can ignore them or fork. Triggers include "deploy to railway", "railway deploy this", "railway logs", "tail railway logs", "why is my railway service crashing", "why did the build fail on railway", "railway 500s", "railway latency", "show railway http logs", "redeploy on railway", "restart my railway service", "roll back railway", "set a railway env var", "list railway variables", "railway metrics", "is my railway service healthy", "connect to my r
    7 repo stars
  11. ▌
    Plan Dag · onsager-ai bundle
    Render the current plan as a high-DPI PNG dependency DAG — nodes are issues / sub-issues / PRs, edges come from sub-issue links plus dependency-language prose ("Depends on", "Part of", "Blocks", "Closes") and PR / commit cross-references, and every node is color-coded done / in-progress / available-next / blocked so sequencing and critical path are obvious at a glance. Use when asked "plan as dag", "draw a dag", "dag diagram", "show the dependency graph", "what's blocking what", "what's the critical path", "what can be parallelized", "what's left for
    7 repo stars
  12. ▌
    Pre Push · onsager-ai
    Run before pushing code on any repo that follows the spec-issue-driven (SDD) loop — catch what CI and reviewers will catch later, and confirm the branch has a linked spec issue in a valid state. Reproduces CI's merge-preview environment, walks the repo's merge-conflict patterns, runs the repo's check gate, and drafts the PR's spec-link line. Triggers include "before push", "ready to push", "pre-push check", "push readiness", "prep for PR", "resolve merge conflict", "merge conflict", "branch has conflicts", "sync with main", or proactively before any git push. Repo-agnostic methodology; the consumer repo's CLAUDE.md and `<repo>-dev-process` overlay the exact gate command and the repo-specific collision patterns.
    7 repo stars
  13. ▌
    CI Triage · onsager-ai
    Triage failed CI runs on a GitHub-Actions–driven repo — classify regression vs flake vs infra, maintain a single rolling `main-red` issue when main is broken, and point humans at the suspect commit. Use when a workflow fails on `main`, or when a human asks "is main red?", "why did CI fail on main?", "triage this workflow run", "classify this failure". Paired with the global `pr-lifecycle` skill (PR-side CI triage) and the `web-testing` skill (invoked for `e2e` failures).
    7 repo stars
  14. ▌
    Codegraph · onsager-ai bundle
    Pre-indexed code knowledge graph (MCP, SQLite + tree-sitter) for faster, lower-token exploration of brownfield codebases. Use when starting work on a repo larger than ~500 files or when the task involves cross-file traversal — "where is X used", "what calls Y", "what breaks if I change Z", "trace flow from A to B", "explain this subsystem". Skip for single-file edits or sessions shorter than the cold-start cost. Triggers include "codegraph", "code graph", "index this repo", "where is X defined", "find callers of", "callees of", "blast radius of changing X", "explore this codebase". Cuts the grep + Read loops needed to orient, via O(1) SQLite lookups and FTS5 search over 8 MCP tools — but it's an unsound tree-sitter approximation, so grep stays the completeness backstop for renames/exhaustive callers.
    7 repo stars
  15. ▌
    Git Commit · onsager-ai
    Best practices for creating clean, atomic git commits with good messages. Use when: (1) staging and committing changes, (2) writing commit messages, (3) deciding what to group in a single commit, (4) handling pre-commit hook failures, (5) choosing between amend and new commit. Triggers on "commit", "stage", "git add", "write a commit message", or "commit my changes".
    7 repo stars
  16. ▌
    Issue Spec · onsager-ai bundle
    Create lean-spec style GitHub issues as specs for human-AI aligned implementation on the current repo. Use when asked to "create a spec", "write a spec issue", "spec this feature", "spec this", or when planning work that needs a specification before implementation. Follows the lean-spec SDD methodology — small focused specs (<2000 tokens), intent over implementation, context economy. Creates GitHub issues with Overview, Design, Plan, Test, Alignment, and Notes sections. Repo-specific area taxonomy, sister-skill names, custom body sections (e.g. Provider impact / Schema impact / Reach), and additional principles are overlaid by the consumer repo's CLAUDE.md and its `*-dev-process` sister skill — read those first when the repo isn't obvious. The `pre-push` and `pr-lifecycle` methodology is shared globally (installed from `onsager-ai/dev-skills`), like this skill.
    7 repo stars
  17. ▌
    Web Testing · onsager-ai
    L2 AI-driven web UI testing for a React/Vite dashboard app. Originally authored against the Onsager Dashboard (the body's route table + file paths are Onsager-shaped); other React dashboards fork the procedure and substitute their own routes / test paths. Use when testing UI on PRs, triaging L1 test failures, or verifying UI behavior at desktop + mobile viewports. Triggers include "test the UI", "check the dashboard", "triage L1 failure", "run L2 tests", "validate this PR", "exploratory test the web app".
    7 repo stars
  18. ▌
    Pr Lifecycle · onsager-ai
    Manage a PR after it's been pushed on any repo that follows the spec-issue-driven (SDD) loop — spec-issue linking, CI triage, review-comment discipline, merge-conflict recovery on open PRs, webhook subscription + the post-push CI sweep, and manual Plan-item / tracker ticking on merge. Triggers include "CI is failing", "check is red", "link this issue", "Closes vs Part of", "respond to review", "subscribe to PR", "triage PR", "the PR is ready", "PR has conflicts", "branch has conflicts with main", "merge conflict on the PR", or when a github-webhook-activity event arrives. Repo-agnostic methodology; the consumer repo's CLAUDE.md and `<repo>-dev-process` overlay the repo-specific CI-failure patterns and any repo-local automation. Paired with `pre-push` (which owns the conflict walkthrough), `issue-spec`, and `ci-triage`.
    7 repo stars
  19. ▌
    Rust Node CI · onsager-ai bundle
    GitHub Actions CI/CD for Rust+Node.js hybrid repos. Covers workflow structure, installable composite actions, artifact flow, caching, and dev versioning. Use when: (1) setting up or fixing GitHub Actions workflows, (2) adding CI for a Rust+Node.js project, (3) working with composite actions (setup-workspace, rust-cross-build, compute-version, wait-npm-propagation), (4) debugging CI failures, (5) setting up the cross-platform build matrix. Triggers on "CI", "workflow", "GitHub Actions", "cross-build", "artifact", or work in .github/workflows/.
    7 repo stars
  20. ▌
    Docs Drift Guard · onsager-ai
    Keep prose docs (architecture overviews, READMEs, ADRs, runbooks) from rotting out of sync with the code they describe. Provides a methodology — the drift-resistance ladder (generated > executed > checked > reviewed > prose), altitude discipline, and one-home-per-fact — plus a concrete CI floor: the zero-dependency `@onsager/docs-drift-check` bin, which fails the gate if any repo-relative link/path a Markdown doc cites no longer resolves. Use when asked to "stop docs drifting", "add a docs drift guard", "keep docs in sync with code", "check doc links in CI", "the architecture doc is stale", "guard this doc", or when writing a doc that will need to stay true as code changes. Repo-agnostic; the consumer repo's CLAUDE.md overlays which docs to guard, how to wire the gate, and which higher rungs to add.
    7 repo stars
  21. ▌
    Rust NPM Publish · onsager-ai bundle
    Publish Rust binaries to npm using the optionalDependencies platform package pattern. Covers the full publish pipeline, version sync, workspace:* protocol, and platform package architecture. Use when: (1) publishing Rust binaries to npm, (2) setting up the platform package pattern (main + per-OS packages), (3) debugging publish failures, (4) managing version sync across pnpm + Cargo workspaces, (5) working with workspace:* protocol. Triggers on "publish", "platform packages", "optionalDependencies", "bin.js", "version sync", "workspace protocol", "npm tag", or "prepare-publish".
    7 repo stars
  22. ▌
    Worktree Devproxy · onsager-ai bundle
    Set up and operate a git-worktree parallel web-dev environment behind a shared Traefik proxy — every worktree runs its own docker compose stack, reachable at http://<worktree>.<repo>.localhost:8000 by Host-header routing, with zero host-port publishing, zero DNS, zero TLS, zero port allocation. Covers: one-time machine setup (Traefik on the `devproxy` network + the `wt` manager script + direnv), onboarding a repo (.envrc, compose Traefik labels, framework adaptations for Vite/Next/etc.), daily usage (wt new/rm/ls), host-run stacks joining the same routing without containers (Traefik file provider + devproxy-route + auto port allocation), and the known failure modes (Docker API version, wrong-network 504s, corporate proxy hijacking localhost, root-owned bind-mount files, stale host-run routes). Triggers on: "worktree dev environment", "devproxy", "wt new", "parallel dev stacks", "Traefik localhost routing", "onboard this repo to the worktree proxy", "set up worktree dev on this machine", "<name>.<repo>.localho
    7 repo stars
  23. ▌
    Github Integration · onsager-ai bundle
    Enable the GitHub CLI (`gh`) in Claude Code cloud sessions and GitHub Copilot coding agent environments. Use this skill when: (1) setting up a project so cloud AI agents can use `gh` for PRs, issues, and releases, (2) configuring setup scripts or SessionStart hooks for `gh` installation, (3) adding `copilot-setup-steps.yml` for GitHub Copilot agents, (4) troubleshooting `gh` auth failures in cloud sessions, or (5) configuring `GH_TOKEN` for headless environments. Triggers on: "enable gh", "github integration", "Claude Code cloud setup", "copilot setup steps", "gh auth in cloud", "gh not working in cloud", "setup script", or any request involving GitHub CLI access from cloud-based AI coding agents.
    7 repo stars
  24. ▌
    Parallel Worktrees · onsager-ai bundle
    Run multiple AI coding agent sessions in parallel using git worktrees — each agent isolated in its own worktree, working on a separate branch. Use this skill whenever the user wants to: run two or more AI agents simultaneously on different features or bugs, set up isolated agent workspaces in the same repo, push parallel branches to GitHub and open/update PRs, coordinate between concurrent agent sessions, or clean up after merging. Triggers on: "parallel agents", "multiple agent sessions", "git worktree", "run agents in parallel", "work on two things at once", "isolated agent workspace", "spin up another agent", or any request involving simultaneous AI-assisted development streams.
    7 repo stars
  25. ▌
    Rust Node Bootstrap · onsager-ai bundle
    Scaffold a new Rust+Node.js hybrid monorepo with pnpm workspaces, Cargo workspace, CI workflows, and publish infrastructure. Use when: (1) starting a new project from scratch, (2) adding missing infrastructure to an existing repo, (3) figuring out the canonical project structure for a Rust+Node.js tool. Triggers on "bootstrap", "scaffold", "new project", "set up project", or "init" in a Rust+Node.js context.
    7 repo stars
  26. ▌
    Worktree Discipline · onsager-ai bundle
    Enforce "no commits on main, agents work in worktrees" with ONE machine-global git pre-commit hook — zero per-repo code. A single `~/.githooks/pre-commit` (installed via `git config --global core.hooksPath`) blocks direct commits to main/master for everyone and blocks main-checkout commits for AI agents (detected via CLAUDECODE=1), scoped automatically to repos onboarded to the worktree-devproxy flow (marker: committed .envrc exporting DEV_HOST), and delegates to each repo's own committed .githooks/pre-commit so repo-specific checks keep running. Use when asked to: "prevent commits on main", "block main commits with githooks", "force agents to use worktrees", "protect main locally", "agents keep committing to the main checkout", or when a pre-commit rejection says "use: wt new <branch>".
    7 repo stars