misty-step

Produce a consistently-styled, self-contained HTML report served privately over Tailscale. One house template (Silver Age comic-ops palette, dark/light toggle, and a mandatory copy-page button) so every report an agent hands the operator looks and behaves the same. Use when: "make an HTML artifact/report", "serve this over tailscale", "write up a brief/report/dashboard as a page", or any time you'd otherwise dump a long analysis into chat. Trigger: /artifact.

Shape a raw idea into something buildable. Product + technical exploration. Spec, design, critique, plan. Output is a context packet. Use when: "shape this", "write a spec", "design this feature", "plan this", "spec out", "context packet", "technical design". Trigger: /shape, /spec, /plan, /cp.

Use when an agent needs release intelligence from Landmark: version analysis, changelog synthesis, release notes, release-kit planning, GitHub Action adoption, fleet rollout, classification, or release artifact evidence. Trigger phrases: "Landmark", "release intelligence", "changelog", "release notes", "version bump", "release kit".

Harness engineering for Harness Kit primitives: skills, shared doctrine, provider roster, harness configs, gates, evals, bootstrap, and sync logic. Use for "improve the harness", "harness engineering", "bootstrap is wrong", "AGENTS.md is stale", "skill health", "skill usage", "undertriggering skill", "description tax", "eval skill", "sync primitives", "roster defaults", "preferred stack", "stack defaults", "hosting defaults", "CI defaults", "observability defaults", "release defaults", "design system defaults", "storage defaults", "agent substrate defaults", "one core many faces", "API CLI MCP SDK skill template", "factory product template", "generate repo-local skill", "bespoke skill subset", "domain agent skill". Trigger: /harness-engineering, /harness, /skill.

Dispatch-shaped code review: fan the diff out to fresh-context reviewers across diverse providers and model families, synthesize, fix blockers, re-review until clean. Use when: "review this", "code review", "is this ready to ship", "second-model review". Trigger: /code-review, /review.

Capture one compounding repo-technical learning while a solved problem is still fresh. Use when: after a bug fix, diagnosis, delivery, review, or incident reveals a reusable pattern worth adding to `docs/solutions/`. Trigger: /compound, /capture-learning, /learning.

Take one ticket or idea from raw intent to merge-ready (or shipped, when asked): context-first, docs→tests→code, live QA, refactor at three altitudes, semantic commits, diverse-provider review, adversarial pre-ship thinking. Use for "deliver this", "build this ticket", "make it merge-ready", "take this end to end". Trigger: /deliver.

Investigate, audit, triage, and fix. Systematic debugging, incident lifecycle, domain auditing, and issue logging. Feedback-loop-first protocol: reproduce or replay before root cause, pattern analysis, hypothesis test, and fix. Use for: any bug, test failure, production incident, error spikes, audit, triage, postmortem, "diagnose", "why is this broken", "debug this", "production down", "is production ok", "audit stripe", "log issues". Trigger: /diagnose.

Use when infrastructure work needs the current Estate map, resource state, declarations, provider readback, an exact plan, or the provider-native management loop. Trigger: /estate-infrastructure, /estate.

Discover and dispatch the agent fleet. Any Roster agent may commission any other agent; there is no declared delegates list. Use when: "delegate this", "dispatch an agent", "who can do this", "hand this to a builder/reviewer/ verifier", "launch a focused agent", or any time work should run in a fresh, independently composed context instead of this one. Trigger: /roster, /dispatch.

Enumerates the peer AI agent CLIs installed on this machine (codex, pi, goose, opencode, claude, cursor-agent, grok, agy, hermes, oracle) and how to invoke each headlessly. A capability map, not a quota: useful for fresh-context adversarial review on a different model family, second opinions, competing attempts, and wide benches. Use when: "ask codex", "ask another model", "second opinion", "cross-model review", "what AI tools do I have", "other agents", "different model family", "adversarial critique from another provider". Trigger: /peer-harnesses.

Prepare credential-free public repository handoffs on dedicated Fly Sprites: remote, isolated, scale-to-zero sandboxes for heavy work. A clean owned checkpoint makes every handoff reproducible without copying workstation, Harness, or Git credentials. Use when: "prepare this on a sprite", "remote sandbox", "offload a public checkout", "bake a sprite", or heavy work that an external launch owner will supervise. Trigger: /sprites, /sprite-lane.

Use when an agent needs to inspect, claim, update, request input for, or complete work cards in a Powder instance. Powder is the self-hostable, agent-first work board: a durable card store with run sessions, activity, audit events, relations, optional proof, and human-in-loop states.

Shape an unresolved idea into a decision and executable context packet. Use when: "shape this", "write a spec", "design this feature", "plan this", "spec out", "context packet", "technical design". Trigger: /shape, /spec, /plan, /cp.

Create or update root VISION.md as a first-class project north-star artifact: conversational interrogation, repo research, philosophy distillation, and wiring repo-local primitives to read it. Use when: "vision", "vision.md", "project vision", "north star", "what is this project", "clarify product direction", "write/update VISION.md", "project philosophy", "why does this repo exist". Trigger: /vision, /north-star.

Grill the operator relentlessly about a plan, decision, or idea by batching every open question into one round instead of asking one at a time. Use when: the operator wants to stress-test their thinking, or uses any 'grill' trigger phrases. Trigger: /grill, /grilling.

Operate Bitterblossom's `bb` event-plane CLI for agent workloads. Use when Codex needs to inspect or run `bb`, configure `plane.toml`, `agents/`, or `tasks/`, dispatch or audit tasks, handle runs, dead letters, recovery, parked tasks, submissions, gates, review-factory workflows, or help another repo consume Bitterblossom. Trigger phrases: "Bitterblossom", "bb", "event plane", "agent workload", "run a task", "inspect runs", "DLQ", "parked task", "submission loop", "review factory".

Dogfood Bitterblossom by using `bb` itself to deliver a Bitterblossom backlog PR, then critique the build, submission, gate, ledger, and operator UX. Use when the user asks to "dogfood Bitterblossom", "bb-dogfood", "work through the Bitterblossom backlog with bb", "use bb on itself", "capture Bitterblossom friction", "run the bb backlog loop", or "test the event plane as its primary user". Trigger: bb-dogfood.

Produce a consistently-styled, self-contained HTML report served privately over Tailscale. One house template (Silver Age comic-ops palette, dark/light toggle, and a mandatory copy-page button) so every report an agent hands the operator looks and behaves the same. Use when: "make an HTML artifact/report", "serve this over tailscale", "write up a brief/report/dashboard as a page", or any time you'd otherwise dump a long analysis into chat. Trigger: /artifact.

Audit, design, and run repo-owned CI gates. Host-agnostic by default: local, GitHub Actions, Azure, or another runner should call the same repo-owned contract. Roster's own gate is fmt/clippy/test plus `cargo run --locked -p roster-cli -- check`; consumer repos keep their own native gate. Use when: "run ci", "check ci", "fix ci", "audit ci", "design CI", "host-agnostic CI", "Dagger", "is ci passing", "run the gates", "why is ci failing", "strengthen ci", "tighten ci", "ci is red", "gates failing", "feedback loop is slow", "run gates less often". Trigger: /ci, /gates.

Dispatch-shaped code review: fan the diff out to fresh-context reviewers across diverse providers and model families, synthesize, fix blockers, re-review until clean. Use when: "review this", "code review", "is this ready to ship", "second-model review". Trigger: /code-review, /review.

Capture one compounding repo-technical learning while a solved problem is still fresh. Use when: after a bug fix, diagnosis, delivery, review, or incident reveals a reusable pattern worth adding to `docs/solutions/`. Trigger: /compound, /capture-learning, /learning.

Convene a council/thinktank: fan one question out to several DISTINCT high-quality OpenRouter model families (via opencode/pi), each carrying a different generative persona/perspective, then synthesize the divergent thinking as chair. Generative deliberation — brainstorm, explore the option space, weigh tradeoffs, decorrelated ideation, lock a contested direction. Distinct from /roster's adversarial critique bench (that finds bugs in an artifact; this generates and reframes). Use when: "convene a council", "thinktank", "council of models", "brainstorm with different models", "get diverse perspectives", "panel of AIs", "what would different experts think", "divergence pass", "ideate broadly", "stress-test this direction with other models". Trigger: /council, /thinktank.

Take one ticket or idea from raw intent to merge-ready (or shipped, when asked): context-first, docs→tests→code, live QA, refactor at three altitudes, semantic commits, diverse-provider review, adversarial pre-ship thinking. Use for "deliver this", "build this ticket", "make it merge-ready", "take this end to end". Trigger: /deliver.

Final mile. Take a branch from merge candidate to shipped: run the /ci + /refactor + /code-review triad in parallel subagents, integrate fixes, and repeat until the branch is lean, green, clean, and shiny. Then archive backlog ticket(s) with Closes-backlog trailers preserved into the squash merge, land it, run /reflect, and apply its outputs. Use when: "ship it", "merge and close out", "final mile", "land and reflect", "finish this ticket". Trigger: /ship.

Accessibility audit, remediation, and verification. WCAG 2.2 AA compliance. Three-agent protocol: audit (find issues) → remediate (fix them) → critique (verify fixes). Use when: "accessibility audit", "a11y", "WCAG", "screen reader", "keyboard navigation", "contrast check", "aria fix", "accessibility sprint", "audit accessibility", "fix accessibility", "a11y issues", "a11y check". Trigger: /a11y

Audit a repo's CI gates, strengthen what is weak, then drive the pipeline green. Owns confidence in correctness — lint, types, tests, coverage, secrets. Dagger is the canonical pipeline owner; absence is auto-scaffolded, not escalated. Acts on its assessment; never returns a report where action would suffice. Never returns red without a structured diagnosis. Bounded self-heal: auto-fix lint/format, regenerate lockfiles, retry flakes. Escalates only genuine algorithm/logic failures. Use when: "run ci", "check ci", "fix ci", "audit ci", "is ci passing", "run the gates", "dagger check", "why is ci failing", "strengthen ci", "tighten ci", "ci is red", "gates failing". Trigger: /ci, /gates.

Analyze, test, and upgrade dependencies. One curated PR, not 47 version bumps. Reachability analysis, behavioral diffs, risk assessment. Package-manager agnostic. Use when: "upgrade deps", "dependency audit", "check for updates", "outdated packages", "security audit deps", "update dependencies", "vulnerable dependencies", "deps". Trigger: /deps.

Backlog management, brainstorming, architectural exploration, project bootstrapping. File-driven backlog via backlog.d/. Parallel investigation bench, synthesis protocol, themed recommendations. Product vision + technical excellence. Use when: backlog session, "groom", "what should we build", "rethink this", "biggest opportunity", "backlog", "prioritize", "tidy", "scaffold". Trigger: /groom, /backlog, /rethink, /moonshot, /scaffold, /tidy.

Browser-based QA, exploratory testing, evidence capture, and bug reporting. Drive running applications and verify they work — not just that tests pass. Use when: "run QA", "test this", "verify the feature", "exploratory test", "check the app", "QA this PR", "capture evidence", "manual testing", "scaffold qa", "generate qa skill". Trigger: /qa.

Unblock, polish, and merge a Volume PR. Fix CI/conflicts/reviews, polish, refactor, land via `gh pr merge <n> --squash --auto`. /land alias runs the final merge. Use when: PR is blocked, CI red, review comments open, "land this", "get this mergeable", "fix and polish", "unblock", "clean up", "make this merge-ready", "address reviews", "fix CI", "land this branch". Trigger: /settle, /land (alias), /pr-fix, /pr-polish.

Shape a raw idea into something buildable. Product + technical exploration. Spec, design, critique, plan. Output is a context packet. Use when: "shape this", "write a spec", "design this feature", "plan this", "spec out", "context packet", "technical design". Trigger: /shape, /spec, /plan, /cp.

Maintain Gradient's repo-local agent harness: skills, agents, settings, repo brief, and gate-aligned instructions. Trigger: /harness, /skill, /primitive.

Take one shaped Gradient docs/schema/profile task to merge-ready. Composes /shape, /implement, /code-review, /ci, /qa, /demo, and /refactor as needed. Stops before merge. Trigger: /deliver.

Assess Gradient's readiness for governed agent work across docs, schemas, profiles, harness, validation, evidence, and public-safe boundaries. Trigger: /agent-readiness, /readiness.

Dialectical premise-and-alternatives audit for a plan, spec, or context packet. Four moves: premise challenge (is this the right problem?), mandatory structurally-distinct alternatives, cross-model outside voice, user-ratified convergence. Named for Gary Tan's plan-ceo-review pattern; operationalizes the AGENTS.md "Diverge Before You Converge" doctrine at the plan-review stage. Use when: about to commit to a plan/spec/design, reviewing a ticket before shape, when "is this the right problem" would be useful, or any time a proposal smells like a symptom fix instead of a root-cause fix. Trigger: /ceo-review, /challenge, /premise-check.

Gradient gate audit and validation workflow. Use when checking whether a docs/profile/schema change is safe to ship in this scaffold. Trigger: /ci.

Review Gradient docs, profiles, schemas, and harness changes for public-safe boundaries, lifecycle consistency, and contract depth. Trigger: /code-review, /review, /critique.

Produce evidence that a Gradient docs/schema/profile change is understandable and reviewable. For this repo, demos are validation transcripts, synthetic fixtures, before/after contract walkthroughs, or release-note blurbs. Trigger: /demo.

Investigate failures in Gradient contracts, docs, schemas, profiles, harness wiring, and future validation commands. Trigger: /diagnose.

Assess and improve codebase readiness for AI coding agents. Dispatches parallel subagents to evaluate style, testing, docs, architecture, CI, observability, security, and dev environment. Produces a scored report with prioritized remediation. Then executes the highest-impact fixes. Use when: "agent readiness", "is this codebase agent-ready", "readiness report", "make this codebase agent-friendly", "agent-ready assessment", "readiness audit", "prepare for agents". Trigger: /agent-readiness, /readiness.

Dialectical premise-and-alternatives audit for a plan, spec, or context packet. Four moves: premise challenge (is this the right problem?), mandatory structurally-distinct alternatives, cross-model outside voice, user-ratified convergence. Operationalizes the AGENTS.md "Diverge Before You Converge" doctrine at the plan-review stage. Use when: about to commit to a plan/spec/design, reviewing a ticket before shape, when "is this the right problem" would be useful, or any time a proposal smells like a symptom fix instead of a root-cause fix. Trigger: /ceo-review, /challenge, /premise-check.

Laboratory CI gate audit and verification workflow. Use when checking whether experiment, harness, analysis, docs, or Spellbook harness changes are safe to ship. Trigger: /ci, /gates.

Parallel multi-agent review for Laboratory changes. Prioritizes correctness, scientific validity, provenance, tests, and harness fit. Trigger: /code-review, /review, /critique.

Take one Laboratory backlog item to merge-ready. Composes /shape, /implement, /code-review, /ci, /refactor, and /qa as needed. Stops before merge. Trigger: /deliver.

Capture and share what changed — every app has a demo path; the format depends on the change and the audience. The spectrum runs from a release-notes blurb ("no demo needed, here's what moved") through a curl + JSON paste, a terminal recording, a screenshot, a GIF, up to a polished narrated launch video. Pick the path that fits the change shape (UI / API / CLI / library / agent tool / internal-only), the audience (PR reviewer / team Slack / external customer), and the time budget. Also scaffolds a project-local demo skill for repos with recurring polished-capture needs. Use when: "make a demo", "generate demo", "record walkthrough", "launch video", "PR evidence", "upload screenshots", "demo artifacts", "make a video", "demo this feature", "create a walkthrough", "show what changed", "paste the output", "release notes blurb", "scaffold demo", "generate demo skill". Trigger: /demo.

Investigate, audit, triage, and fix. Systematic debugging, incident lifecycle, domain auditing, and issue logging. Four-phase protocol: root cause → pattern analysis → hypothesis test → fix. Use for: any bug, test failure, production incident, error spikes, audit, triage, postmortem, "diagnose", "why is this broken", "debug this", "production down", "is production ok", "audit stripe", "log issues". Trigger: /diagnose.

Outer loop for Laboratory research work. Picks a backlog item, shapes it, delivers it, settles it, ships it through PR, monitors evidence, and reflects. Trigger: /flywheel.

Final mile for scry. Land a merge-ready backlog branch, archive the shipped backlog files into backlog.d/_done/ before squash, preserve backlog trailers in the squash commit, pull master, invoke /reflect, and route any reflect harness edits to harness/reflect-outputs. Assumes /settle already proved the branch merge-ready against scry's Quality Checks merge-gate; /ship does not refactor, review, or run a fresh CI campaign. Use when: "ship it", "merge and close out", "land this scry ticket", "finish this backlog item", "merge and reflect". Trigger: /ship.

Dialectical premise-and-alternatives audit for a plan, spec, or context packet. Four moves: premise challenge (is this the right problem?), mandatory structurally-distinct alternatives, cross-model outside voice, user-ratified convergence. Named for Gary Tan's plan-ceo-review pattern; operationalizes the AGENTS.md "Diverge Before You Converge" doctrine at the plan-review stage. Use when: about to commit to a plan/spec/design, reviewing a ticket before shape, when "is this the right problem" would be useful, or any time a proposal smells like a symptom fix instead of a root-cause fix. Trigger: /ceo-review, /challenge, /premise-check.

Run and repair scry's actual quality gates. The ship gate is GitHub Actions Quality Checks merge-gate, with pnpm local parity and Lefthook as defense in depth. This repo does not use Dagger; never scaffold it or describe it as canonical here. Bounded self-heal may fix lint, formatting, stale generated artifacts, and obvious focus markers, but must not lower coverage, weaken TypeScript, disable tests, or bypass audit. Use when: "run ci", "check ci", "fix ci", "audit ci", "is ci passing", "run the gates", "why is ci failing", "strengthen ci", "tighten ci", "ci is red", "gates failing". Trigger: /ci, /gates.

Parallel multi-agent code review for scry. Launch reviewer team, synthesize findings, auto-fix blocking issues, loop until clean. Use when: "review this", "code review", "is this ready to ship", "check this code", "review my changes". Trigger: /code-review, /review, /critique.

Safe Convex schema/data migrations in scry, including schema removals, dry-runs, diagnostics, target verification, and production approval gates.

scry inner-loop composer. Takes one file-driven backlog item from backlog.d/ to merge-ready code by composing /shape -> /implement -> {/code-review + /ci + /refactor + /qa as applicable}. Stops at merge-ready. Does not push, merge, deploy, archive backlog tickets, or inject backlog-closing trailers; /ship owns closure. Use when: building one shaped backlog item, "deliver this", "make it merge-ready", driving one scry ticket through implementation, review, verification, and evidence. Trigger: /deliver.

Deploy scry to its real production surface: Convex backend first, validation second, Vercel frontend last. This skill is approval-gated for every command that can mutate non-local Convex or Vercel state. It stops at a healthy deploy receipt and hands ongoing observation to /monitor. Use when: "deploy scry", "ship to production", "release", "run the production deploy", "deploy this merged ref". Trigger: /deploy, /ship-it, /release.

scry-specific diagnosis for bugs, test failures, production incidents, Sentry/Vercel/Convex triage, Langfuse cost or quality anomalies, prompt eval regressions, and durable issue logging. Reproduce first, prove root cause, then fix and verify against the scry gate. Use for: "diagnose", "debug", "why is this broken", "production down", "is production ok", "Sentry issue", "Convex deploy failed", "migration failed", "generation quality dropped", "cost spike", "prompt eval failed", "audit", "triage", "log issues". Trigger: /diagnose.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, border radius, optical alignment, font smoothing, tabular numbers, image outlines, box shadows.

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.

Use when an agent needs production observability from Canary: uptime, health checks, check-ins, incidents, error timelines, service evidence, webhook responder context, API keys, SDK integration, or agent-readable operational truth. Trigger phrases: "Canary", "production debugging", "incident", "health check", "error log", "monitor", "observability".

Operate Canary's dedicated-host deployment and disaster-recovery runbook: verify Litestream-to-S3 status, inspect the canary.service/container boundary, and run non-destructive restore drills. Misty Step production runs at canary.mistystep.io on a dedicated DigitalOcean host. Use when: "deploy canary", "check canary backups", "is canary backed up", "restore drill", "DR check", "canary disaster recovery". Trigger: /canary-deploy.

QA Canary changes by exercising the real running service, not just tests. Canary is a self-hosted agent observability service: an Axum HTTP API (ingest/health/query/webhooks) over one SQLite writer, plus a `canary` inspection CLI and a TypeScript SDK. "Tests pass" is not QA. Use when: "QA this", "verify the feature", "smoke test canary", "check the API", "test canary". Trigger: /canary-qa.

Generate and verify paid fal.ai video renders for the DoomScrum swipe feed. Use when: "regenerate content", "render the feed", "new renders", "bake-off a model", "switch video model", "re-roll a clip", or any task that spends FAL money. Trigger: /render-feed.

Operate DoomScrum from this repo: run the swipe-feed server, generate local feed renders, check dispatch readiness, and garbage-collect generated state. Use when asked to operate, diagnose, or clean up DoomScrum itself. Trigger: /doomscrum.

Project-local demo path for DoomScrum: recut the Remotion marketing video from verified feed renders and deliver MP4s to the Desktop. Use when: "recut the demo", "regenerate the demo", "demo video", "make the demo harder/faster/more brainrot". Trigger: /demo.

QA Cerberus changes by exercising the real review pipeline, not just tests. Cerberus is a code-review runner (Rust contracts + a master reviewer over an OpenCode/OMP substrate), so "verify.sh green" proves the machinery, NOT that the reviewer is good. "Tests pass" is not QA. Use when: "QA this", "verify the reviewer", "smoke test cerberus", "did the doctrine/prompt change help", "test the review". Trigger: /cerberus-qa.

Run Cerberus as an agent-native code reviewer. Use when an agent needs a review of a local git range, a verdict-gated exit code, an MCP review tool, artifact rendering/validation, or GitHub PR posting through an explicit caller-injected token. Do not use for generic code review advice without a checkout or ReviewArtifact.v1.

Use when an agent needs release intelligence from Landmark: version analysis, changelog synthesis, release notes, release-kit planning, GitHub Action adoption, fleet rollout, classification, or release artifact evidence. Trigger phrases: "Landmark", "release intelligence", "changelog", "release notes", "version bump", "release kit".

Dogfood Landmark fleet adoption and release-note automation across GitHub repositories. Use when asked to integrate Landmark into personal or organization repos, run fleet scan/plan/open-prs, evaluate adoption friction, capture release-pipeline evidence, or turn dogfood findings into Landmark fixes/backlog.