Productivity

cyz26 Bundle

Capture task-time learnings in Codex repositories, keep `learning-log.md` and `status.md` aligned, and safely triage promotions into durable knowledge or skill candidates.

cyz26 Skill

Use when executing one approved OpenSpec task or configured lightweight ledger item.

cyz26 Bundle

Plan-first Godot engineering for feature implementation, bug fixing, architecture review, and performance diagnosis with official-doc routing and explicit validation. Use for day-to-day Godot project work when the task is not primarily a scene-interface refactor, preset-driven release/export task, Web deployment incident, or Web CJK font failure.

cyz26 Skill

Use when initializing DevFlow workflow files or restoring a missing project control plane.

cyz26 Skill

Use when triaging features, bugs, refactors, migrations, tooling, or workflow requests.

cyz26 Skill

Use when workflow state, specs, tasks, evidence, dependencies, or generated guidance drift.

cyz26 Bundle

Use when DevFlow has upgraded, when refreshing the local/global DevFlow plugin installation or installed cache, or when refreshing DevFlow project-local workflow configuration across active projects.

cyz26 Skill

Use when checkpointing or preparing /compact at workflow boundaries.

cyz26 Bundle

Diagnose Godot runtime, scene-loading, editor, or export failures and drive toward the smallest defensible fix. Use when the task is driven by an error, regression, crash, null instance, missing node path, failed load, or export failure, including breakage caused by an earlier rename or move. Do not use for ordinary feature requests or planned refactors.

cyz26 Skill

Close out tasks or run periodic durable-knowledge reviews in any Codex repo that uses AGENTS.md + docs/work + knowledge/, keeping task metadata, long-term docs, verification state, and emerging skill candidates in sync.

cyz26 Bundle

Use when Codex should delegate a complete bounded planning, review, or explicitly approved execution task to Claude Code through the DevFlow wrapper, then independently verify the result.

cyz26 Skill

Use when routing Codex setup, planning, execution, verification, or workflow repair.

cyz26 Bundle

Execute or diagnose a Godot preset-driven export and release workflow. Use only when the task explicitly asks to export, prepare a release, or debug an export-specific failure. Do not use for ordinary feature work or scene refactors.

cyz26 Bundle

Route Godot WeChat and Douyin mini-game work through a shared solution workflow covering adoption, refresh, validation, upstream monitoring, and platform-specific triage. Use when a Godot project needs the reusable mini-game package installed or updated, when a repo should keep thin wrappers around `addons/minigame_solution/`, when Codex must check latest official or external solution drift and dependency updates, or when Codex must decide whether to load the WeChat or Douyin mini-game workflow for validation and debugging.

dauquangthanh Bundle

Logs daily standup notes from content the user pastes in. Extracts blockers into a tracked impediments list. Does NOT facilitate the standup — the team runs the meeting and tells the AI what happened. Use when recording daily standup notes, tracking impediments, or logging what each team member did yesterday / today / blocked on.

dauquangthanh Bundle

Drafts the User Acceptance Testing (UAT) plan for a feature or release. UAT is a customer-owned phase distinct from system testing: it verifies that the delivered system meets business objectives in a production-like environment with real or representative users. Produces scope, entry/exit criteria, environments, participant roster, test scenarios (business-workflow level), execution schedule, sign-off ledger, and defect escalation rules. Does not facilitate the UAT session itself. Use when a Waterfall project approaches the verification phase, when a customer contract requires formal UAT sign-off, or when distinguishing UAT from QA system testing.

buildpad-ai Skill

Spec-driven development (SDD) methodology for Buildpad DaaS apps. Use when starting a new project, feature, or significant change, or when requirements are unclear. Routes work through the spec workflow — requirements.md (EARS) → design.md → tasks.md in .kiro/specs/ — via the buildpad-spec-* skills, or Kiro's native specs when working in Kiro.

buildpad-ai Skill

Verify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.

buildpad-ai Skill

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.

buildpad-ai Skill

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.

buildpad-ai Skill

Decomposes specs into implementable tasks. Use when you have a spec or feature description and need to break it into small, verifiable tasks with acceptance criteria and dependency ordering.

marvin-lijunzan Bundle

Use when a complex repository task needs ChatGPT web reasoning while Codex remains responsible for local evidence, edits, and tests.

marvin-lijunzan Bundle

Collects PaperSpine workflow options and writes config for flash/pro, scene, language, and inputs.

ferroxlabs Skill

Generate a GDPR / data-processing assessment, DPA template (controller-to-processor), or sub-processor disclosure. Covers Article 28 obligations, SCCs for international transfers, DPIA triggers, and data-subject-rights workflow. Templates only - not legal advice. Have a privacy attorney review before signing.

ferroxlabs Skill

Vendor W-9 collection workflow, 1099-NEC vs 1099-MISC vs 1099-K decision tree, contractor classification check (IRS 20-factor + ABC test embedded), TIN matching, backup withholding triggers. Templates only - not personalized tax advice.

ferroxlabs Skill

Write a HARO (Help A Reporter Out) or Qwoted/SourceBottle expert-source reply that gets quoted - not buried. Opens with a credentialed one-liner that answers "why this person, for this query," delivers the answer in 3-5 tight bullets with specifics and a contrarian take, and closes with a pull quote written to be lifted verbatim. Use when responding to a journalist query on HARO, Qwoted, SourceBottle, or similar journalist-source services where you have genuine expertise and a 2-4 hour reply window. Not for writing cold pitches to journalists (use content-press-release + pitch email) and not for full press release drafting (use content-press-release).

ferroxlabs Skill

Analyze accounts receivable aging, calculate DSO, and generate compliant collection email sequences for overdue invoices. FDCPA / state-UDAP-aware language; intent-gated escalation; SOL-aware bad-debt write-off guidance. Ported from Anthropic's reconciliation skill, hardened for SMB liability surface.

johnqtcg Bundle

Use when creating or refactoring GitHub Actions CI workflows for Go repositories. Covers repository-shape detection, Make-driven delegation with formal fallbacks, Go setup, caching, tool pinning, permissions, reusable workflows, and quality gate design.

creatorland Skill

Internal CS skill — for one customer account, map what skills/workflows they COULD be running against their plan tier, then write a short "3 things to try this week" email with paste-ready prompts to drive activation and beat churn. Use when the user says "usage pulse for <account>", "CS health check", "what should this account be using", "write an activation nudge", or a CSM is prepping an account review. Deliverable is a per-account health read plus a ready-to-send email. v1 reads the billing/usage dashboard manually — no account-telemetry tool exists yet (wishlist item 5).

nexadevapp Skill

Discovers and invokes Nexa skills. Use when starting a session or to identify which skill is appropriate for the task at hand. This is the orchestrator skill which governs how all Nexa skills are discovered and invoked.

nexadevapp Bundle

Creates technical task specification documents for engineering work that has no user-facing scenario: configuration, cleanup, dependency updates, infrastructure, and developer experience improvements. Use when the user asks to "create a technical task", "set up the database", "bump a dependency", "add a dev profile", "clean up code", or mentions infrastructure tasks, configuration changes, or maintenance work.

grasscaograss Skill

Debugging workflow for welding planning failures in the Weldone project. Triggered when the user reports a planning error (e.g., "SolvePath Failed!", IndexOutOfRangeException in PrePlanScanWeldDualArmAsyncInSameExternal, ParseWeldSeamGroups failure, or "single seam works but multiple fails"). Covers dual-arm scan/weld transition planning, external axis pre-planning, and workpiece seam group parsing.

mindgoblinstudios Bundle

(grim:dev:tiramisu-task-decomp): (Tiramisu): Convert an imperative plan into a functional dependency diagram (DAG) and subagent-ready task packets. Use when the user wants to decompose a plan into parallelizable, dependency-safe execution steps.

mindgoblinstudios Bundle

Postmaster (Email Triage): Inbox shredder. Triage your mail. Keep what needs a reply, file what's waiting, and turn noise into confetti.

davie521 Skill

Ultra-compressed communication mode. Substantially cuts token usage by dropping filler, articles, and pleasantries while keeping full technical accuracy. Designed for English output; limited effect on Chinese conversations. TRIGGER only on explicit invocation: user says "caveman mode", "talk like caveman", "use caveman", or invokes /caveman. DO NOT TRIGGER when user merely asks for a short or concise answer — that is a one-off style request, not a switch into this persistent mode.

oliver-kriska Bundle

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.