Q00
- 96 skills
- 0 followers
- 6.4k repo stars
- last month last updated
- ▌
- ▌ Ce Dhh Rails Style · q00 bundleThis skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the "clarity over cleverness" philosophy.
- ▌ Openwarden 2 · q00Use when the user wants a Warden review from an SSOT issue, roadmap, RFC, or brief. Turns a canonical source link plus active work surfaces into an evidence-backed alignment review without implementing, approving, merging, or force-closing work.
- ▌ Ce Debug 2 · q00 bundleSystematically find root causes and fix bugs. Use when debugging errors, investigating test failures, reproducing bugs from issue trackers (GitHub, Linear, Jira), or when stuck on a problem after failed fix attempts. Also use when the user says 'debug this', 'why is this failing', 'fix this bug', 'trace this error', or pastes stack traces, error messages, or issue references.
- ▌ Ce Strategy 2 · q00 bundleCreate or maintain STRATEGY.md - the product's target problem, approach, users, key metrics, and tracks of work. Use when starting a new product, updating direction, or when prompts like 'write our strategy', 'update the roadmap', 'what are we working on', or 'set up the strategy doc' come up. Also triggers when ce-ideate, ce-brainstorm, or ce-plan need upstream grounding and no strategy doc exists yet.
- ▌ Ce Demo Reel 2 · q00 bundleCapture a visual demo reel (GIF, terminal recording, screenshots) for PR descriptions. Use when shipping UI changes, CLI features, or any work with observable behavior that benefits from visual proof. Also use when asked to add a demo, record a GIF, screenshot a feature, show what changed visually, create a demo reel, capture evidence, add proof to a PR, or create a before/after comparison.
- ▌
- ▌ Oc 2 · q00 bundlePrimary public entry point for OpenClip. Use this skill instead of any oc-* worker whenever a user provides a video or asks for video editing, shorts/reels/clips, cut editing, captions/subtitles/translation, thumbnails, long-form assembly, or multi-video composition in any language. It also owns capability gaps: choose agent judgment vs a built-in oc command, reuse or author audited toolbox tools, and prepare a user-approved upstream proposal when a proven tool should reach other users.
- ▌ Oc Verifier 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Independent adversarial gate-reviewer. Verifies that a deliverable actually meets its contract — NOT by trusting the renderer's "success", but by probing observable evidence and the video-specific adversarial failure classes. The only pass verdict is "confirmed". Spawn AFTER a render/cut/clip stage, separate from whoever produced it.
- ▌ Oc Assembler 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Renders final deliverables from a plan: stitches multiple sources/sections into one longform, or renders a batch of shorts/hooks (with aspect + burned subs). The "hands" of flow 3 and the render half of flow 1. Use after cut/hook decisions are locked.
- ▌ Oc Cut Judge 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Reconciles the competing cut proposals (filler / pacing / narrative) for ONE section into a single final keep-EDL. Resolves conflicts: narrative can veto an over-aggressive filler cut; filler can override narrative's "keep everything". Writes the section EDL file. Use after cut-proposers return for a section.
- ▌ Oc Toolsmith 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Extends the harness itself. When a task needs a capability the built-in `oc` verbs don't cover, the toolsmith FIRST checks the learned toolbox for an existing tool to reuse, and only if none fits AUTHORS a new script, verifies it with a self-test, and registers it so every future run can reuse it. This is how the harness self-improves.
- ▌ Oc Stt Worker 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Transcribes ONE audio chunk. This is the parallel fan-out unit for STT — the orchestrator spawns one worker per chunk index so a long video is transcribed concurrently. Use after `oc ingest` has produced chunks.
- ▌ Oc Hook Finder 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Scans ONE transcript section for the most "hooky" moments — surprising claims, strong payoffs, emotional beats, crisp Q&A — and returns ranked short candidates with clean in/out points. Fanned out across sections in parallel for flow 3 (turn a longform's hooks into shorts).
- ▌ Oc Cut Proposer 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Proposes how to cut ONE transcript section, through a single editorial LENS (filler / pacing / narrative). The orchestrator fans out 2-3 proposers with different lenses over the same section so they DEBATE the cut. Returns a keep/cut EDL with per-decision rationale. Does not render.
- ▌ Oc Orchestrator 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Top-level control plane for the OpenClip video harness. Reads a flow manifest, fans out worker subagents in parallel (STT, cut-editing debate, subtitles, thumbnails, assembly), and merges their structured results. Use when a user wants to turn long video(s) into cut-edited originals, shorts, long-form, thumbnails, or subtitled deliverables.
- ▌ Oc Tool Auditor 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Adversarial gate for promoting a LOCAL learned tool into SHARED memory. Assumes the tool is broken or malicious until proven otherwise. Independent of the tool's author. Only its approval (recorded via `oc toolbox promote --reviewed`) lets a tool become shared and reusable by other sessions/people.
- ▌ Oc Subtitle Agent 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Builds SRT subtitles for a clip or full video from the merged transcript, with optional translation and hard burn-in. Use whenever a deliverable needs captions — shorts (burned), long-form (sidecar), or multilingual exports.
- ▌ Oc Proxy Converter 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Converts DJI .LRF / GoPro .LRV (or any high-res source) into a lightweight, playable review proxy mp4. Use as the first step of flow 1 when the input is a low-res proxy file or when a downscaled review copy is needed.
- ▌ Oc Thumbnail Artist 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Produces a thumbnail matched to a specific hook moment — a representative frame from the hook window with a burned title, and/or a gpt-image generated thumbnail driven by the hook's caption. One per short/long deliverable. Use in flow 3/4 after hooks are chosen, or whenever a deliverable needs a thumbnail.
- ▌ Oc Thumbnail Designer 2 · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Designs a publish-grade thumbnail for one deliverable: real speaker identity (persona photo via gpt-image edit), a curated style preset, content-aware prompting from the actual transcript, and a locally typeset headline. Self-reviews its renders against an anti-slop checklist, iterates, and learns the channel's taste over time (oc taste). Use whenever a thumbnail should look designed — famous-tech-YouTuber grade — instead of a frame grab.
- ▌ Ce Debug · q00 bundleSystematically find root causes and fix bugs. Use when debugging errors, investigating test failures, reproducing bugs from issue trackers (GitHub, Linear, Jira), or when stuck on a problem after failed fix attempts. Also use when the user says 'debug this', 'why is this failing', 'fix this bug', 'trace this error', or pastes stack traces, error messages, or issue references.
- ▌ Ce Strategy · q00 bundleCreate or maintain STRATEGY.md - the product's target problem, approach, users, key metrics, and tracks of work. Use when starting a new product, updating direction, or when prompts like 'write our strategy', 'update the roadmap', 'what are we working on', or 'set up the strategy doc' come up. Also triggers when ce-ideate, ce-brainstorm, or ce-plan need upstream grounding and no strategy doc exists yet.
- ▌ Ce Demo Reel · q00 bundleCapture a visual demo reel (GIF, terminal recording, screenshots) for PR descriptions. Use when shipping UI changes, CLI features, or any work with observable behavior that benefits from visual proof. Also use when asked to add a demo, record a GIF, screenshot a feature, show what changed visually, create a demo reel, capture evidence, add proof to a PR, or create a before/after comparison.
- ▌
- ▌ Ce Setup · q00 bundleDiagnose and configure compound-engineering environment. Checks CLI dependencies, plugin version, and repo-local config. Offers guided installation for missing tools. Use when troubleshooting missing tools, verifying setup, or before onboarding.
- ▌ Ce Optimize · q00 bundleRun metric-driven iterative optimization loops -- define a measurable goal, run parallel experiments, measure each against hard gates or LLM-as-judge scores, keep improvements, and converge on the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation.
- ▌ Ce Polish Beta · q00 bundle[BETA] Start the dev server, open the feature in a browser, and iterate on improvements together.
- ▌ Ce Slack Research · q00Search Slack for interpreted organizational context -- decisions, constraints, and discussion arcs -- and produce a synthesized research digest with cross-cutting analysis. Use when the user says 'search slack for', 'what did we discuss about', 'slack context for', or 'what does the team think about'. Differs from slack:find-discussions, which returns raw message results without synthesis.
- ▌ Ce Frontend Design · q00Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done.
- ▌ Refine · q00 bundleMerge meaning gaps from Reflect into one user-approved shared meaning. In the Socrates loop, Refine writes only the current cycle's ### Refine section. Triggers (EN): refine, create shared meaning, merge meanings, consolidate intent Do NOT use when: expanding meanings (-> wonder), comparing meaning gaps (-> reflect), restating a goal (-> restate), or running the full Seed loop (-> socrates) vs reflect: Reflect exposes differences; Refine turns the accepted differences into one shared meaning.
- ▌ Wonder · q00 bundleExpand a vague word or request by asking what other meanings may be hidden inside it. In the Socrates loop, Wonder writes only the current cycle's ### Wonder section. Triggers (EN): wonder, expand meaning, explore hidden meanings, what else could this mean Do NOT use when: comparing meaning gaps (-> reflect), merging meanings (-> refine), restating a goal (-> restate), or running the full Seed loop (-> socrates) vs reflect: Wonder expands meaning candidates; Reflect compares those candidates against the user's intended meaning.
- ▌ Reflect · q00 bundleCompare meaning candidates from Wonder with the user's intended meaning, one pair at a time. In the Socrates loop, Reflect writes only the current cycle's ### Reflect section. Triggers (EN): reflect, compare meanings, surface meaning gap, check what I meant Do NOT use when: expanding meanings (-> wonder), merging meanings into shared meaning (-> refine), restating a goal (-> restate), or running the full Seed loop (-> socrates) vs wonder: Wonder expands candidates; Reflect checks where each candidate matches or diverges from the user's intention.
- ▌ Restate · q00 bundleRestate the shared meaning from Refine as one executable goal sentence. In the Socrates loop, Restate writes only the current cycle's ### Restate section. Triggers (EN): restate, restate goal, one-line goal, turn this into a goal Do NOT use when: expanding meanings (-> wonder), comparing meanings (-> reflect), creating shared meaning (-> refine), or running the full Seed loop (-> socrates) vs refine: Refine creates shared meaning; Restate turns that shared meaning into a goal another person can execute.
- ▌ Ontology · q00 bundleAdd a semantic boundary layer on top of a closed Seed. Use Seed.goal as idea, ask for boundary and exactly three properties, and replace the top-level ## Ontology section in .symposium/scratch/socrates.md. Triggers (EN): ontology, create ontology, define semantic boundary, add meaning boundary Do NOT use when: no Seed exists yet (-> socrates), Seed content must evolve (-> evolve-step), or the full convergence harness is needed (-> interview-harness) vs evolve-step: Evolve-step changes the Seed; Ontology adds a boundary layer above the Seed.
- ▌ Socrates · q00 bundleRun Wonder, Reflect, Refine, and Restate as a Ralph-style loop to turn one vague request into a closed Seed with goal, constraints, and acceptance_criteria. The latest Seed is stored in .symposium/scratch/socrates.md under the top-level ## Seed section. Triggers (EN): socrates, run socrates, create seed, clarify vague request, close this request into a seed Do NOT use when: a Seed already exists and only blind spots need review (-> evolve-step), convergence through ontology is needed (-> interview-harness), or only one meaning-expansion step is needed (-> wonder) vs interview-harness: Socrates creates the Seed; Interview Harness continues with evolve-step and ontology convergence.
- ▌ Evolve Step · q00 bundleReview an existing Seed for blind spots, ask two blind-spot questions, and apply only user-approved changes to create the next Seed. The latest Seed replaces the top-level ## Seed section in .symposium/scratch/socrates.md; audit history is appended to .symposium/scratch/evolve-step.md. Triggers (EN): evolve-step, evolve seed, seed blind spots, seed v1 v2, review blind spots Do NOT use when: creating the first Seed from a vague request (-> socrates), running convergence through ontology (-> interview-harness), or only defining semantic boundary (-> ontology) vs socrates: Socrates creates Seed v1; Evolve-step turns an existing Seed into a user-approved next Seed.
- ▌ Interview Harness · q00 bundleRun Socrates, Evolve-step, and Ontology as a semi-automatic convergence loop. If a complete Seed already exists, skip Socrates. Iterate evolve-step and ontology until ontology similarity reaches 0.85 or the safety valve stops the loop. Triggers (EN): interview-harness, run interview harness, converge seed, socratic harness, close this into a seed Do NOT use when: only expanding meaning (-> wonder), only creating the initial Seed (-> socrates), only reviewing blind spots (-> evolve-step), or only defining semantic boundary (-> ontology) vs socrates: Socrates creates the Seed; Interview Harness continues through blind-spot review and ontology convergence.
- ▌ Oc · q00 bundlePrimary public entry point for OpenClip. Use this skill instead of any oc-* worker whenever a user provides a video or asks for video editing, shorts/reels/clips, cut editing, captions/subtitles/translation, thumbnails, long-form assembly, or multi-video composition in any language. It also owns capability gaps: choose agent judgment vs a built-in oc command, reuse or author audited toolbox tools, and prepare a user-approved upstream proposal when a proven tool should reach other users.
- ▌ Oc Verifier · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Independent adversarial gate-reviewer. Verifies that a deliverable actually meets its contract — NOT by trusting the renderer's "success", but by probing observable evidence and the video-specific adversarial failure classes. The only pass verdict is "confirmed". Spawn AFTER a render/cut/clip stage, separate from whoever produced it.
- ▌ Oc Assembler · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Renders final deliverables from a plan: stitches multiple sources/sections into one longform, or renders a batch of shorts/hooks (with aspect + burned subs). The "hands" of flow 3 and the render half of flow 1. Use after cut/hook decisions are locked.
- ▌ Oc Cut Judge · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Reconciles the competing cut proposals (filler / pacing / narrative) for ONE section into a single final keep-EDL. Resolves conflicts: narrative can veto an over-aggressive filler cut; filler can override narrative's "keep everything". Writes the section EDL file. Use after cut-proposers return for a section.
- ▌ Oc Toolsmith · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Extends the harness itself. When a task needs a capability the built-in `oc` verbs don't cover, the toolsmith FIRST checks the learned toolbox for an existing tool to reuse, and only if none fits AUTHORS a new script, verifies it with a self-test, and registers it so every future run can reuse it. This is how the harness self-improves.
- ▌ Oc Stt Worker · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Transcribes ONE audio chunk. This is the parallel fan-out unit for STT — the orchestrator spawns one worker per chunk index so a long video is transcribed concurrently. Use after `oc ingest` has produced chunks.
- ▌ Openclip · q00 bundleCodex app entrypoint for running OpenClip: transcript-first shorts, 10-minute long-form candidates, subagent review, thumbnails, multilingual SRTs, and manifest verification from a local video.
- ▌ Oc Hook Finder · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Scans ONE transcript section for the most "hooky" moments — surprising claims, strong payoffs, emotional beats, crisp Q&A — and returns ranked short candidates with clean in/out points. Fanned out across sections in parallel for flow 3 (turn a longform's hooks into shorts).
- ▌ Oc Cut Proposer · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Proposes how to cut ONE transcript section, through a single editorial LENS (filler / pacing / narrative). The orchestrator fans out 2-3 proposers with different lenses over the same section so they DEBATE the cut. Returns a keep/cut EDL with per-decision rationale. Does not render.
- ▌ Oc Orchestrator · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Top-level control plane for the OpenClip video harness. Reads a flow manifest, fans out worker subagents in parallel (STT, cut-editing debate, subtitles, thumbnails, assembly), and merges their structured results. Use when a user wants to turn long video(s) into cut-edited originals, shorts, long-form, thumbnails, or subtitled deliverables.
- ▌ Oc Tool Auditor · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Adversarial gate for promoting a LOCAL learned tool into SHARED memory. Assumes the tool is broken or malicious until proven otherwise. Independent of the tool's author. Only its approval (recorded via `oc toolbox promote --reviewed`) lets a tool become shared and reusable by other sessions/people.
- ▌ Oc Subtitle Agent · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Builds SRT subtitles for a clip or full video from the merged transcript, with optional translation and hard burn-in. Use whenever a deliverable needs captions — shorts (burned), long-form (sidecar), or multilingual exports.
- ▌ Oc Proxy Converter · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Converts DJI .LRF / GoPro .LRV (or any high-res source) into a lightweight, playable review proxy mp4. Use as the first step of flow 1 when the input is a low-res proxy file or when a downscaled review copy is needed.
- ▌ Oc Thumbnail Artist · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Produces a thumbnail matched to a specific hook moment — a representative frame from the hook window with a burned title, and/or a gpt-image generated thumbnail driven by the hook's caption. One per short/long deliverable. Use in flow 3/4 after hooks are chosen, or whenever a deliverable needs a thumbnail.
- ▌ Oc Thumbnail Designer · q00Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Designs a publish-grade thumbnail for one deliverable: real speaker identity (persona photo via gpt-image edit), a curated style preset, content-aware prompting from the actual transcript, and a locally typeset headline. Self-reviews its renders against an anti-slop checklist, iterates, and learns the channel's taste over time (oc taste). Use whenever a thumbnail should look designed — famous-tech-YouTuber grade — instead of a frame grab.
- ▌ Lfg · q00 bundleRun the full autonomous engineering pipeline end-to-end (plan, work, code review, test, commit, push, open PR, watch CI, fix CI failures until green). Use only when the user explicitly requests hands-off execution of a software task and provides a feature description; do not auto-route casual conversation here.
- ▌ Ce Plan · q00 bundleCreate structured plans for multi-step tasks -- software features, research workflows, events, study plans, or any goal that benefits from breakdown. Also deepens existing plans with interactive sub-agent review. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a brainstorm doc is ready for planning. Use 'deepen the plan' or 'deepening pass' for the deepening flow. For exploratory requests, prefer ce-brainstorm first.
- ▌
- ▌ Ce Proof · q00 bundleRun human-in-the-loop review loops over markdown via Proof (proofeditor.ai) — share, view, comment on, edit, and sync collaborative docs. Use when the user says "view this in proof", "share to proof", "HITL this doc", or wants a shared markdown review surface for a spec, plan, or draft, including handoffs from ce-brainstorm, ce-ideate, or ce-plan. Do not trigger on "proof" meaning evidence, math proofs, proof-of-concept, or "proofread this".
- ▌ Ce Commit · q00Create a git commit with a clear, value-communicating message. Use when the user says "commit", "commit this", "save my changes", "create a commit", or wants to commit staged or unstaged work. Produces well-structured commit messages that follow repo conventions when they exist, and defaults to conventional commit format otherwise.
- ▌ Ce Ideate · q00 bundleGenerate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.
- ▌ Ce Update · q00 bundleCheck if the compound-engineering plugin is up to date and recommend the update command if not. Use when the user says "update compound engineering", "check compound engineering version", "ce update", "is compound engineering up to date", "update ce plugin", or reports issues that might stem from a stale compound-engineering plugin version. This skill only works in Claude Code — it relies on the plugin harness cache layout.
- ▌
- ▌ Ce Sessions · q00 bundleSearch and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened recently, or any question about past agent sessions. Also use when the user references prior sessions, previous attempts, or past investigations — even without saying 'sessions' explicitly.
- ▌ Ce Work Beta · q00 bundle[BETA] Execute work with external delegate support. Same as ce-work but includes experimental Codex delegation mode for token-conserving code implementation.
- ▌ Ce Brainstorm · q00 bundleExplore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.
- ▌ Ce Doc Review · q00 bundleReview requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.
- ▌
- ▌ Ce Code Review · q00 bundleStructured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.
- ▌ Ce Product Pulse · q00 bundleGenerate a time-windowed pulse report on what users experienced and how the product performed - usage, quality, errors, signals worth investigating. Use when the user says 'run a pulse', 'show me the pulse', 'how are we doing', 'weekly recap', 'launch-day check', or passes a time window like '24h' or '7d'. Configures via .compound-engineering/config.local.yaml and saves reports to docs/pulse-reports/.
- ▌ Ce Release Notes · q00 bundleSummarize recent compound-engineering plugin releases, or answer a specific question about a past release with a version citation. Use when the user types `/ce-release-notes` or asks "what changed in compound-engineering recently?" or "what happened to `<skill-name>`?".
- ▌ Ce Simplify Code · q00Simplify and refine recently changed code for clarity, reuse, quality, and efficiency while preserving behavior.
- ▌ Ce Commit Push Pr · q00 bundleCommit, push, and open a PR with an adaptive, value-first description that scales in depth with the change. Use when the user says "commit and PR", "ship this", "create a PR", or "open a pull request". Also handles description-only flows ("write a PR description", "rewrite the PR body", "describe this PR") without committing or pushing.
- ▌ Ce Compound Refresh · q00 bundleRefresh stale learning and pattern docs under docs/solutions/ by reviewing them against the current codebase, then updating, consolidating, or deleting drifted ones. Use when the user asks to "refresh my learnings", "audit docs/solutions/", "clean up stale learnings", or "consolidate overlapping docs", or when ce-compound flags an older doc as superseded. Do not trigger for general refactor, debugging, or code-review work unless the user has explicitly pointed at docs/solutions/.
- ▌ Ce Resolve Pr Feedback · q00 bundleResolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.
- ▌ Vercel Optimize · q00 bundleUse for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.
- ▌ Openwarden · q00Use when the user wants a Warden review from an SSOT issue, roadmap, RFC, or brief. Turns a canonical source link plus active work surfaces into an evidence-backed alignment review without implementing, approving, merging, or force-closing work.
- ▌
- ▌ Unstuck · q00Break through stagnation with lateral thinking personas — single or multi-persona debate
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Ooo · q00Start Ouroboros onboarding. Use when the user sends bare `ooo`, asks to start Ouroboros, or is using Ouroboros for the first time.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Ouroboros Config · q00Open or drive the Ouroboros settings GUI (browser, TUI, or conversational fallback)
- ▌
- ▌
- ▌
- ▌ Pm · q00Generate a PM through guided PM-focused interview with automatic question classification. Use when the user says 'ooo pm', 'prd', 'product requirements', or wants to create a PRD/PM document.
- ▌ Resume Session · q00List in-flight Ouroboros sessions and show the commands needed to re-attach after MCP disconnect