ArcadeAI
- 65 skills
- 0 followers
- 7 hours ago last updated
- ▌ Elicit 2 · arcadeaiExtract tacit knowledge through non-obvious microquestions — things only the user knows that can't be found in code, docs, or research. Use when you're about to guess at intent, context, or constraints during SAFEWORD's understanding flow. Also use when user says 'ask me', 'what do you need to know', or when another skill (bdd, brainstorm, debug) needs user context before proceeding. Do NOT use for questions answerable by reading the codebase or searching the web.
- ▌ Verify 3 · arcadeaiVerify ticket completion criteria — use when finishing a ticket, before marking work done, or checking acceptance criteria. Runs tests, build, lint, scenarios, and dependency drift checks.
- ▌ Explain 3 · arcadeaiUse when you need safeword's dense artifacts or current state translated into plain English — what this is, why it matters, what to do next, with the internal jargon stripped. Targets a safeword ticket, a blocked gate, or a verdict; with no target it recaps where you are in the current safeword work. Read-only. Do NOT use to explain code diffs or PRs (base Claude handles those), for general status questions unrelated to safeword artifacts, or to make any change.
- ▌ Testing 2 · arcadeaiHow to write good tests. Use when writing tests, improving test coverage, or evaluating test quality. Also invoked by other skills — BDD at RED phase, tdd-review at GREEN gate, refactor at PROTECT phase, and debug. Core test quality knowledge across all workflows.
- ▌ Closeout 3 · arcadeaiClose a completed local delivery safely. Use when wrapping up a finished coding session by verifying it, merging only with explicit authority, capturing retrospective learning, and cleaning the exact merged branch and worktree. Do NOT use for cloud-agent tasks, unmerged work, or cleanup without a pull request.
- ▌ Refactor 2 · arcadeaiImprove code structure without changing behavior. Use when refactoring, restructuring, simplifying, or extracting code. Also for reducing duplication, renaming for clarity, or addressing code smells. Enforces one change → test → commit when the commit can stay scoped. NOT for style/formatting (use $safeword:lint), features, or bug fixes.
- ▌ Tdd Review 2 · arcadeaiQuality check for a completed TDD step. Runs when safeword's TDD flow finishes RED, GREEN, or REFACTOR; not a user-facing entry point.
- ▌ Retro Filer 3 · arcadeaiFiles Safeword's sanitized retro spool upstream. Only when a trusted Stop continuation or authenticated closeout guard names a spool path.
- ▌ Review Spec 3 · arcadeaiUse when authoring or reviewing a ticket's scenarios (`.feature` source, with legacy test-definitions.md fallback). Authoring mode gives define-behavior the same standard before drafting that Review mode applies independently at scenario-gate. NOT for spec.md JTBD/criteria/persona framing — that is self-review.
- ▌ Self Review 3 · arcadeaiRuns when safeword's review gate asks for a spec review — an inline self-review of the just-authored spec.md that earns its Tier 1 review stamp. Not a user-facing entry point, and never spawns a sub-agent.
- ▌ Pr Readiness 3 · arcadeaiPrepare a pull request for human review and decide whether it may leave Draft. Use when creating or rewriting a PR description, marking a PR ready, responding to review, or checking whether a change is mergeable. Keeps incomplete evidence Draft. Do NOT use as a substitute for human approval or repository merge policy.
- ▌ Figure It Out 2 · arcadeaiExplore and debate options with fresh documentation and research before committing. Use for a real decision with multiple plausible approaches — library/framework choice, architecture, API/schema design, algorithm selection, or a costly communication/strategy call. Enumerates research domains, checks current docs and evidence-based methods, and weighs options on correctness, elegance, and bloat. Do NOT use for divergent ideation (brainstorm), extracting user intent (elicit), or reviewing finished work (quality-review).
- ▌ Finish Review 3 · arcadeai bundleUse only right after the shared review coordinator reports it's run out of reviewer routes; a bounded internal fallback, not something a user invokes directly.
- ▌ Quality Review 3 · arcadeaiDeep review of any work-product — code, docs, specs, plans, decisions — grounded in current authoritative sources. Use when double-checking against latest docs, verifying versions or claims, checking security, or pressure-testing correctness and elegance before something ships. Complements the automatic quality hook with ecosystem verification. NOT for divergent ideation (brainstorm), weighing still-open options (figure-it-out), your own spec's framing (self-review), or scenario review (review-spec).
- ▌ Cleanup Zombies 3 · arcadeaiKill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.
- ▌ Lint 2 · arcadeaiRun linters and formatters to fix code style issues. Use when cleaning up style violations, formatting code, or after implementation to ensure code meets project standards.
- ▌ Audit 2 · arcadeaiRun a diff-scoped code audit for architecture, dead code, and test quality. Uses the change from main to focus feature reviews; request a repository audit for whole-codebase discovery.
- ▌ Verify 2 · arcadeaiVerify ticket completion criteria — use when finishing a ticket, before marking work done, or checking acceptance criteria. Runs tests, build, lint, scenarios, and dependency drift checks.
- ▌ Explain 2 · arcadeaiUse when you need safeword's dense artifacts or current state translated into plain English — what this is, why it matters, what to do next, with the internal jargon stripped. Targets a safeword ticket, a blocked gate, or a verdict; with no target it recaps where you are in the current safeword work. Read-only. Do NOT use to explain code diffs or PRs (base Claude handles those), for general status questions unrelated to safeword artifacts, or to make any change.
- ▌ Closeout 2 · arcadeaiClose a completed local delivery safely. Use when wrapping up a finished coding session by verifying it, merging only with explicit authority, capturing retrospective learning, and cleaning the exact merged branch and worktree. Do NOT use for cloud-agent tasks, unmerged work, or cleanup without a pull request.
- ▌ Retro Filer 2 · arcadeaiFiles Safeword's sanitized retro spool upstream. Only when a trusted Stop continuation or authenticated closeout guard names a spool path.
- ▌ Review Spec 2 · arcadeaiUse when authoring or reviewing a ticket's scenarios (`.feature` source, with legacy test-definitions.md fallback). Authoring mode gives define-behavior the same standard before drafting that Review mode applies independently at scenario-gate. NOT for spec.md JTBD/criteria/persona framing — that is self-review.
- ▌ Self Review 2 · arcadeaiRuns when safeword's review gate asks for a spec review — an inline self-review of the just-authored spec.md that earns its Tier 1 review stamp. Not a user-facing entry point, and never spawns a sub-agent.
- ▌ Pr Readiness 2 · arcadeaiPrepare a pull request for human review and decide whether it may leave Draft. Use when creating or rewriting a PR description, marking a PR ready, responding to review, or checking whether a change is mergeable. Keeps incomplete evidence Draft. Do NOT use as a substitute for human approval or repository merge policy.
- ▌ Finish Review 2 · arcadeai bundleUse only right after the shared review coordinator reports it's run out of reviewer routes; a bounded internal fallback, not something a user invokes directly.
- ▌ Quality Review 2 · arcadeaiDeep review of any work-product — code, docs, specs, plans, decisions — grounded in current authoritative sources. Use when double-checking against latest docs, verifying versions or claims, checking security, or pressure-testing correctness and elegance before something ships. Complements the automatic quality hook with ecosystem verification. NOT for divergent ideation (brainstorm), weighing still-open options (figure-it-out), your own spec's framing (self-review), or scenario review (review-spec).
- ▌ Cleanup Zombies 2 · arcadeaiKill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.
- ▌ Bdd 2 · arcadeai bundleBehavior-first feature development — use when building new capabilities, continuing feature work, or when work introduces new state or multiple user flows. Discovers desired behavior through examples and scenarios before implementation. Do NOT use for bug fixes, typos, or small isolated changes.
- ▌ Lint 3 · arcadeaiRun linters and formatters to fix code style issues. Use when cleaning up style violations, formatting code, or after implementation to ensure code meets project standards.
- ▌ Audit 3 · arcadeaiRun a diff-scoped code audit for architecture, dead code, and test quality. Uses the change from main to focus feature reviews; request a repository audit for whole-codebase discovery.
- ▌ Debug 2 · arcadeaiRoot cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.
- ▌ Retro 2 · arcadeaiRun a safeword retrospective on the current session on demand — pull friction (bugs / rough edges / gaps) out of the session transcript and file it upstream through the outbound safety check. Use when the user says "run a retro", "$safeword:retro", "retrospective on this session", or wants to capture friction before the session ends. The retro also auto-fires at Stop; this is the manual, on-demand path.
- ▌ Spike 2 · arcadeaiRun a bounded disposable experiment to resolve one build-only technical uncertainty before production planning. Use only when explicitly invoked.
- ▌ Quality Reviewer · arcadeaiDeep code quality review with web research. Use when user explicitly requests verification against latest docs ('double check against latest', 'verify versions', 'check security'), needs deeper analysis beyond automatic hook, or is working on projects without SAFEWORD.md/CLAUDE.md. Fetches current documentation (WebFetch), checks latest versions (WebSearch), and provides deep analysis (performance, security, alternatives).
- ▌ Linear Issue · arcadeaiAutomate the complete Linear issue workflow - fetch issue, update status to In Progress, create branch, implement, test, create PR, and move to In Review
- ▌ Build Arcade MCP Tool · arcadeai bundleBuild and deploy custom MCP tools using the Arcade MCP framework. Use when the user wants to create, build, scaffold, or deploy an MCP tool or server to Arcade Cloud, or when working with arcade_mcp_server, MCPApp, @tool decorators, arcade deploy, or Arcade tool development.
- ▌ Build Custom User Verifier · arcadeaiBuild a custom user verifier server for Arcade.dev in any language. Use when implementing Arcade's user verification flow, building an /auth/verify endpoint, integrating Arcade tool authorization into a production app, or troubleshooting verification issues like missing user_id or session cookies during the OAuth callback.
- ▌ Bdd · arcadeai bundleBehavior-first feature development — use when building new capabilities, continuing feature work, or when work introduces new state or multiple user flows. Discovers desired behavior through examples and scenarios before implementation. Do NOT use for bug fixes, typos, or small isolated changes.
- ▌ Lint · arcadeaiRun linters and formatters to fix code style issues. Use when cleaning up style violations, formatting code, or after implementation to ensure code meets project standards.
- ▌ Audit · arcadeaiRun a diff-scoped code audit for architecture, dead code, and test quality. Uses the change from main to focus feature reviews; request a repository audit for whole-codebase discovery.
- ▌ Debug · arcadeaiRoot cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.
- ▌ Retro · arcadeaiRun a safeword retrospective on the current session on demand — pull friction (bugs / rough edges / gaps) out of the session transcript and file it upstream through the outbound safety check. Use when the user says "run a retro", "/retro", "retrospective on this session", or wants to capture friction before the session ends. The retro also auto-fires at Stop; this is the manual, on-demand path.
- ▌ Spike · arcadeaiRun a bounded disposable experiment to resolve one build-only technical uncertainty before production planning. Use only when explicitly invoked.
- ▌ Elicit · arcadeaiExtract tacit knowledge through non-obvious microquestions — things only the user knows that can't be found in code, docs, or research. Use when you're about to guess at intent, context, or constraints during SAFEWORD's understanding flow. Also use when user says 'ask me', 'what do you need to know', or when another skill (bdd, brainstorm, debug) needs user context before proceeding. Do NOT use for questions answerable by reading the codebase or searching the web.
- ▌ Verify · arcadeaiVerify ticket completion criteria — use when finishing a ticket, before marking work done, or checking acceptance criteria. Runs tests, build, lint, scenarios, and dependency drift checks.
- ▌ Explain · arcadeaiUse when you need safeword's dense artifacts or current state translated into plain English — what this is, why it matters, what to do next, with the internal jargon stripped. Targets a safeword ticket, a blocked gate, or a verdict; with no target it recaps where you are in the current safeword work. Read-only. Do NOT use to explain code diffs or PRs (base Claude handles those), for general status questions unrelated to safeword artifacts, or to make any change.
- ▌ Testing · arcadeaiHow to write good tests. Use when writing tests, improving test coverage, or evaluating test quality. Also invoked by other skills — BDD at RED phase, tdd-review at GREEN gate, refactor at PROTECT phase, and debug. Core test quality knowledge across all workflows.
- ▌ Closeout · arcadeaiClose a completed local delivery safely. Use when wrapping up a finished coding session by verifying it, merging only with explicit authority, capturing retrospective learning, and cleaning the exact merged branch and worktree. Do NOT use for cloud-agent tasks, unmerged work, or cleanup without a pull request.
- ▌ Refactor · arcadeaiImprove code structure without changing behavior. Use when refactoring, restructuring, simplifying, or extracting code. Also for reducing duplication, renaming for clarity, or addressing code smells. Enforces one change → test → commit when the commit can stay scoped. NOT for style/formatting (use /lint), features, or bug fixes.
- ▌ Brainstorm · arcadeaiUse when the user wants to explore options, weigh approaches, or think through uncertainty before committing to a direction. Collaborative brainstorming and rubber ducking — divergence-first thinking partner.
- ▌ Tdd Review · arcadeaiQuality check for a completed TDD step. Runs when safeword's TDD flow finishes RED, GREEN, or REFACTOR; not a user-facing entry point.
- ▌ Versioning · arcadeaiSafeword semver commitment and release discipline. Use when bumping versions, cutting releases, deciding what goes in a patch vs minor vs major, or reviewing changelog entries. Also use when auto-upgrade logic needs to know what's safe to apply silently.
- ▌ Retro Filer · arcadeaiFiles Safeword's sanitized retro spool upstream. Only when a trusted Stop continuation or authenticated closeout guard names a spool path.
- ▌ Review Spec · arcadeaiUse when authoring or reviewing a ticket's scenarios (`.feature` source, with legacy test-definitions.md fallback). Authoring mode gives define-behavior the same standard before drafting that Review mode applies independently at scenario-gate. NOT for spec.md JTBD/criteria/persona framing — that is self-review.
- ▌ Self Review · arcadeaiRuns when safeword's review gate asks for a spec review — an inline self-review of the just-authored spec.md that earns its Tier 1 review stamp. Not a user-facing entry point, and never spawns a sub-agent.
- ▌ Pr Readiness · arcadeaiPrepare a pull request for human review and decide whether it may leave Draft. Use when creating or rewriting a PR description, marking a PR ready, responding to review, or checking whether a change is mergeable. Keeps incomplete evidence Draft. Do NOT use as a substitute for human approval or repository merge policy.
- ▌ Check Retros · arcadeai bundleInspects SafeWord's production retro collector, durable relay, receipts, and filed GitHub issues. Use when checking whether retros are flowing, investigating a receipt or queue state, or reviewing recent retro submissions. Do not use to submit a retro or mutate production recovery state.
- ▌ Figure It Out · arcadeaiExplore and debate options with fresh documentation and research before committing. Use for a real decision with multiple plausible approaches — library/framework choice, architecture, API/schema design, algorithm selection, or a costly communication/strategy call. Enumerates research domains, checks current docs and evidence-based methods, and weighs options on correctness, elegance, and bloat. Do NOT use for divergent ideation (brainstorm), extracting user intent (elicit), or reviewing finished work (quality-review).
- ▌ Finish Review · arcadeai bundleUse only right after the shared review coordinator reports it's run out of reviewer routes; a bounded internal fallback, not something a user invokes directly.
- ▌ Ticket System · arcadeaiTicket system and work logs for context anchoring. Use when creating tickets, managing work logs, or anchoring context across multi-step tasks or sessions. Do NOT use for simple patches or single-step tasks.
- ▌ Quality Review · arcadeaiDeep review of any work-product — code, docs, specs, plans, decisions — grounded in current authoritative sources. Use when double-checking against latest docs, verifying versions or claims, checking security, or pressure-testing correctness and elegance before something ships. Complements the automatic quality hook with ecosystem verification. NOT for divergent ideation (brainstorm), weighing still-open options (figure-it-out), your own spec's framing (self-review), or scenario review (review-spec).
- ▌ Cleanup Zombies · arcadeaiKill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.
- ▌ Demand Research · arcadeaiTests whether a proposed product bet has credible demand. Use when Why now depends on an unresolved, decision-critical demand claim or when the user explicitly asks for demand research. Do NOT use for child features, mandated work, parity work, or when a cheaper experiment can answer the question before research.
- ▌
- ▌ Build Error Adapter · arcadeaiBuild new Arcade error adapters from scratch using public Arcade TDK patterns. Use when adding provider integrations, mapping SDK exceptions, or extending HTTP/GraphQL/auth adapter behavior.