← all publishers

ArcadeAI

@arcadeai source repo

Report this profile Claim this profile

• 91 skills
• 0 followers
• last month last updated

1. ▌
   Brainstorm 3 · arcadeai

   Use 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.
   15 installs
2. ▌
   Ticket System 3 · arcadeai

   Ticket 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.
   9 installs
3. ▌
   Bdd 3 · arcadeai bundle

   Behavior-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.
   9 installs
4. ▌
   Debug 3 · arcadeai

   Root cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.
   12 installs
5. ▌
   Retro 3 · arcadeai

   Run 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.
   14 installs
6. ▌
   Spike 3 · arcadeai

   Run a bounded disposable experiment to resolve one build-only technical uncertainty before production planning. Use only when explicitly invoked.
   13 installs
7. ▌
   Elicit 3 · arcadeai

   Extract 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.
   10 installs
8. ▌
   Lint 4 · arcadeai

   Run 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.
   11 installs
9. ▌
   Testing 3 · arcadeai

   How 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.
   11 installs
10. ▌
    Audit 4 · arcadeai

    Run 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.
    11 installs
11. ▌
    Refactor 3 · arcadeai

    Improve 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.
    11 installs
12. ▌
    Verify 4 · arcadeai

    Verify 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.
    12 installs
13. ▌
    Explain 4 · arcadeai

    Use 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.
    12 installs
14. ▌
    Brainstorm 2 · arcadeai

    Use 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.
    11 installs
15. ▌
    Tdd Review 3 · arcadeai

    Quality check for a completed TDD step. Runs when safeword's TDD flow finishes RED, GREEN, or REFACTOR; not a user-facing entry point.
    11 installs
16. ▌
    Closeout 4 · arcadeai

    Close 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.
    13 installs
17. ▌
    Figure It Out 3 · arcadeai

    Explore 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).
    13 installs
18. ▌
    Ticket System 2 · arcadeai

    Ticket 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.
    15 installs
19. ▌
    Retro Filer 4 · arcadeai

    Files Safeword's sanitized retro spool upstream. Only when a trusted Stop continuation or authenticated closeout guard names a spool path.
    10 installs
20. ▌
    Review Spec 4 · arcadeai

    Use 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.
    11 installs
21. ▌
    Self Review 4 · arcadeai

    Runs 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.
    9 installs
22. ▌
    Pr Readiness 4 · arcadeai

    Prepare 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.
    12 installs
23. ▌
    Demand Research 2 · arcadeai

    Tests 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.
    10 installs
24. ▌
    Finish Review 4 · arcadeai bundle

    Use 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.
    9 installs
25. ▌
    Quality Review 4 · arcadeai

    Deep 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).
    11 installs
26. ▌
    Cleanup Zombies 4 · arcadeai

    Kill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.
    9 installs
27. ▌
    Elicit 2 · arcadeai

    Extract 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.
    10 installs
28. ▌
    Verify 3 · arcadeai

    Verify 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.
    8 installs
29. ▌
    Explain 3 · arcadeai

    Use 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.
    11 installs
30. ▌
    Testing 2 · arcadeai

    How 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.
    12 installs
31. ▌
    Closeout 3 · arcadeai

    Close 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.
    10 installs
32. ▌
    Refactor 2 · arcadeai

    Improve 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.
    13 installs
33. ▌
    Tdd Review 2 · arcadeai

    Quality check for a completed TDD step. Runs when safeword's TDD flow finishes RED, GREEN, or REFACTOR; not a user-facing entry point.
    13 installs
34. ▌
    Retro Filer 3 · arcadeai

    Files Safeword's sanitized retro spool upstream. Only when a trusted Stop continuation or authenticated closeout guard names a spool path.
    12 installs
35. ▌
    Review Spec 3 · arcadeai

    Use 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.
    11 installs
36. ▌
    Self Review 3 · arcadeai

    Runs 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.
    14 installs
37. ▌
    Pr Readiness 3 · arcadeai

    Prepare 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.
    12 installs
38. ▌
    Figure It Out 2 · arcadeai

    Explore 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).
    14 installs
39. ▌
    Finish Review 3 · arcadeai bundle

    Use 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.
    9 installs
40. ▌
    Quality Review 3 · arcadeai

    Deep 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).
    15 installs
41. ▌
    Cleanup Zombies 3 · arcadeai

    Kill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.
    8 installs
42. ▌
    Lint 2 · arcadeai

    Run 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.
    12 installs
43. ▌
    Audit 2 · arcadeai

    Run 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.
    14 installs
44. ▌
    Verify 2 · arcadeai

    Verify 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.
    11 installs
45. ▌
    Explain 2 · arcadeai

    Use 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.
    11 installs
46. ▌
    Closeout 2 · arcadeai

    Close 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.
    11 installs
47. ▌
    Retro Filer 2 · arcadeai

    Files Safeword's sanitized retro spool upstream. Only when a trusted Stop continuation or authenticated closeout guard names a spool path.
    11 installs
48. ▌
    Review Spec 2 · arcadeai

    Use 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.
    8 installs
49. ▌
    Self Review 2 · arcadeai

    Runs 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.
    12 installs
50. ▌
    Pr Readiness 2 · arcadeai

    Prepare 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.
    14 installs
51. ▌
    Finish Review 2 · arcadeai bundle

    Use 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.
    13 installs
52. ▌
    Quality Review 2 · arcadeai

    Deep 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).
    9 installs
53. ▌
    Cleanup Zombies 2 · arcadeai

    Kill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.
    11 installs
54. ▌
    Bdd 2 · arcadeai bundle

    Behavior-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.
    11 installs
55. ▌
    Lint 3 · arcadeai

    Run 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.
    12 installs
56. ▌
    Audit 3 · arcadeai

    Run 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.
    12 installs
57. ▌
    Debug 2 · arcadeai

    Root cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.
    13 installs
58. ▌
    Retro 2 · arcadeai

    Run 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.
    14 installs
59. ▌
    Spike 2 · arcadeai

    Run a bounded disposable experiment to resolve one build-only technical uncertainty before production planning. Use only when explicitly invoked.
    7 installs
60. ▌
    Quality Reviewer · arcadeai

    Deep 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).
    13 installs
61. ▌
    Linear Issue · arcadeai

    Automate the complete Linear issue workflow - fetch issue, update status to In Progress, create branch, implement, test, create PR, and move to In Review
    11 installs
62. ▌
    Build Arcade MCP Tool · arcadeai bundle

    Build 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.
    12 installs
63. ▌
    Build Custom User Verifier · arcadeai

    Build 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.
    9 installs
64. ▌
    Bdd · arcadeai bundle

    Behavior-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.
    11 installs
65. ▌
    Lint · arcadeai

    Run 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.
    13 installs
66. ▌
    Audit · arcadeai

    Run 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.
    9 installs
67. ▌
    Debug · arcadeai

    Root cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.
    9 installs
68. ▌
    Retro · arcadeai

    Run 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.
    8 installs
69. ▌
    Spike · arcadeai

    Run a bounded disposable experiment to resolve one build-only technical uncertainty before production planning. Use only when explicitly invoked.
    9 installs
70. ▌
    Elicit · arcadeai

    Extract 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.
    15 installs
71. ▌
    Verify · arcadeai

    Verify 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.
    12 installs
72. ▌
    Explain · arcadeai

    Use 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.
    12 installs
73. ▌
    Testing · arcadeai

    How 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.
    13 installs
74. ▌
    Closeout · arcadeai

    Close 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.
    14 installs
75. ▌
    Refactor · arcadeai

    Improve 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.
    9 installs
76. ▌
    Brainstorm · arcadeai

    Use 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.
    8 installs
77. ▌
    Tdd Review · arcadeai

    Quality check for a completed TDD step. Runs when safeword's TDD flow finishes RED, GREEN, or REFACTOR; not a user-facing entry point.
    10 installs
78. ▌
    Versioning · arcadeai

    Safeword 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.
    12 installs
79. ▌
    Retro Filer · arcadeai

    Files Safeword's sanitized retro spool upstream. Only when a trusted Stop continuation or authenticated closeout guard names a spool path.
    12 installs
80. ▌
    Review Spec · arcadeai

    Use 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.
    9 installs
81. ▌
    Self Review · arcadeai

    Runs 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.
    9 installs
82. ▌
    Pr Readiness · arcadeai

    Prepare 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.
    10 installs
83. ▌
    Check Retros · arcadeai bundle

    Inspects 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.
    11 installs
84. ▌
    Figure It Out · arcadeai

    Explore 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).
    11 installs
85. ▌
    Finish Review · arcadeai bundle

    Use 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.
    9 installs
86. ▌
    Ticket System · arcadeai

    Ticket 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.
    13 installs
87. ▌
    Quality Review · arcadeai

    Deep 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).
    10 installs
88. ▌
    Cleanup Zombies · arcadeai

    Kill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.
    10 installs
89. ▌
    Demand Research · arcadeai

    Tests 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.
    11 installs
90. ▌
    Safeword Plugin Setup · arcadeai

    Restore the Safeword Codex profile plugin for this project.
    10 installs
91. ▌
    Build Error Adapter · arcadeai

    Build 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.
    12 installs