superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Shipd commands and skills, namespaced under /s:
Plugin s from marketplace shipd in shipd-now/shipd. Commands read from the repo's manifest — yesterday.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
code-reviewRun a semdiff-grounded semantic review of this pull request: map the changed files into cohorts, reason over the bundled engine's syntax-aware structural diff instead of raw file dumps, chase changed signatures to their call sites, and report findings with a high/medium/low severity rubric and a shi
askConsult the oracle before interrupting a person — one compact question answered from durable knowledge, or queued for a human. Trigger phrases: "ask the oracle", "consult the oracle", "/s:ask".
autopilotDrive an approved epic's members to shipped pull requests unattended. Trigger phrases: "autopilot", "deliver", "ship the epic", "/s:autopilot".
demoProduce a branded demo video, routing a browser subject to `record` and a terminal subject to `tape`, both converging on `post`. Trigger phrases: "record a demo", "make a demo video", "/s:demo".
doctorDiagnose the shipd environment with the read-only preflight, then run only the remedies the user consents to. Trigger phrases: "doctor", "fix my setup", "check my environment", "preflight", "/s:doctor".
documentAuthor or revise documentation against the shipd documentation standard, then lint it clean — docs only, nothing shipped. Trigger phrases: "document this", "write the docs", "rewrite this doc", "/s:document".
driftJudge whether an epic's gated plans still hold against main — holds, revise, or conflict per drifted member. Trigger phrases: "drift", "check drift", "has the plan drifted", "/s:drift".
driveDrive a real browser with Playwright to operate an app and verify a change against it, ending on a PASS/FAIL verdict. Records browser footage for /s:demo. Trigger phrases: "drive the app", "verify this in the browser", "click through this flow", "/s:drive".
duckTalk an idea through with the adversarial Rubber Duck agent — read-only critique, nothing changed. Trigger phrases: "rubber duck", "talk through this idea", "validate this concept", "be my duck", "/s:duck".
epic-grillPlan every unplanned member of an approved epic in one pass, ask every open decision in one final round, then reconcile and gate the plans together and hand off to /s:autopilot on a green preflight. Trigger phrases: "grill an epic", "plan the whole epic", "/s:epic-grill".
epicDecompose a feature into an epic — shared decisions, design, and a stub table of member changes — then stop. Trigger phrases: "epic", "create an epic", "decompose", "amend the epic", "/s:epic".
explainRead a shipd epic through the engine and explain it in under 100 lines — with a diagram only where one carries structure. Trigger phrases: "explain this epic", "summarize the epic", "what is this epic about", "/s:explain".
fixDebug a reported problem against the spec library, fix the code, and stop at the report. Trigger phrases: "fix this bug", "debug this", "find and fix", "/s:fix".
forgetRemove one captured preference from the personal memory store, confirmed first — the remove counterpart to `/s:remember`. Trigger phrases: "forget that", "remove a memory", "delete a memory", "forget my preference", "/s:forget".
gateSet up the shipd semantic review gate in a repository, taking consent before anything changes on GitHub. Trigger phrases: "set up the gate", "install the review gate", "block PRs on review", "/s:gate", "/s:gate update", "update the gate".
initSet up shipd in a project — a guided first-run wizard, or one section on demand — through the engine's init and config verbs. Trigger phrases: "set up shipd", "initialise shipd", "shipd setup wizard", "/s:init".
initiativeDrive workspace initiatives — author, list, review a brief, or attach one to an epic — through the engine's verbs. Trigger phrases: "initiative", "brief", "attach an initiative", "/s:initiative".
memoryList the durable preferences captured in the personal memory store — the read-only browse counterpart to `/s:remember`. Trigger phrases: "show my memories", "list my memories", "what do you remember", "browse memory", "/s:memory".
onboardRun the guided nine-step shipd tour the user drives one step at a time. Trigger phrases: "onboarding", "onboard", "tour", "how does shipd work", "teach me shipd", "/s:onboard", "/s:onboard next", "/s:onboard back".
plan-deepWalk one spec's riskiest pieces step by step, edit in place, and re-gate — epic-aware. Trigger phrases: "plan deep", "deep plan", "walk the spec", "/s:plan-deep".
planConverge context into an execution-ready spec, then stop. Trigger phrases: "plan", "spec this", "plan before building", "/s:plan".
prWrite a shipd pull request's title and body, then create or update the pull request and print its URL. Trigger phrases: "open the PR", "write the PR description", "retitle the PR", "/s:pr".
prdInterrogate a product idea into a lint-clean workspace PRD, installed through the engine's staged emit. Trigger phrases: "PRD", "product requirements", "discover phase", "/s:prd".
rememberCapture the user's durable preferences into the personal memory store as `memory-*` pages, through one confirmed, staged write. Trigger phrases: "remember I prefer", "capture a preference", "save to memory", "note that", "/s:remember".
researchTurn a question into a cited research report, installed through the engine so an epic can link it. Trigger phrases: "research", "deep research", "research report", "/s:research".
reviewRun a semantic review of local changes against a base ref before they are pushed. Trigger phrases: "review my changes", "semantic review", "review this diff", "/s:review".
roomTake this agent's turn in a pull request's room — join, read, wait for a task, reply in prose (an author agent may fix its own finding), and stop cleanly. Trigger phrases: "join the PR room", "answer the room", "take my turn in the room", "/s:room".
statusReport a change's lifecycle status, or run a guarded transition. Trigger phrases: "status", "validate change", "set status", "pipeline", "/s:status".
teachDistill this repo's spec artifacts and answered queue entries into the workspace wiki through one staged, lint-gated write. Trigger phrases: "teach the oracle", "distill knowledge into the wiki", "drain the queue", "/s:teach".
video-ingestTurn a screen recording into a grounded, cited intent brief installed through the engine. Trigger phrases: "video ingest", "ingest this recording", "turn this video into a brief", "/s:video-ingest".
workspaceSet up and inspect the shipd workspace — init, show, clone, or sync — through the engine's workspace verbs. Trigger phrases: "workspace", "set up a workspace", "workspace init", "clone a workspace", "sync the workspace", "materialize members", "map the workspace", "team workspace", "/s:workspace".
worktree-hooksAuthor and register the setup scripts a fresh worktree runs, through the engine's worktree hooks verbs. Trigger phrases: "worktree hook", "post-worktree script", "set up new worktrees", "run this in every worktree", "/s:worktree-hooks".
sub-agentExecution worker on a shipd spec-driven build — claims tasks from the coordinator and implements them exactly per the change artifacts, never guessing.
teacherPost-verify teacher for a spec-driven build — distils one verified change's durable knowledge into the workspace wiki through one staged, lint-gated write, bounded and best-effort.
validatorIndependent adversarial validator for a spec-driven build — refutes each delta scenario by exercising the real code and reports a per-scenario verdict.
python3 "${CLAUDE_PLUGIN_ROOT}/skills/document/scripts/voice_digest.py"
python3 "${CLAUDE_PLUGIN_ROOT}/skills/workspace/scripts/store_sync.py"
python3 "${CLAUDE_PLUGIN_ROOT}/skills/workspace/scripts/store_sync.py"
python3 "${CLAUDE_PLUGIN_ROOT}/skills/build/scripts/guardrails.py"
python3 "${CLAUDE_PLUGIN_ROOT}/skills/build/scripts/guardrails.py"
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.