Productivity

miyako Bundle

Run a 4D project from the command line with tool4d or the full 4D application: the invocation protocol to follow, a task router, version requirements, binary paths, flags, startup-method patterns, automated testing, and the DIALOG + CALL FORM render cycle. Ships installable source for six ready-made startup methods that capture or execute a form. Use when executing 4D code headlessly, capturing form output, or wiring 4D into CI.

ozlar34 Bundle

Generate a structured mid-session handoff block. Invoke proactively when remaining context drops to ~15% and meaningful task state would otherwise be lost; also on explicit /session-handoff. Persists to ~/.claude/handoffs/ and copies to clipboard so a fresh session can resume without losing state. Supports `--minimal` for a bare-bones block.

qinbatista Bundle

Use for code creation, repair, refactoring, and code review when writing style, structure, or lifecycle decisions matter. Provides general preferences with Python and Unity C# references. Exact read-only lookups and mechanical commands need no code-design workflow.

qinbatista Bundle

Verify consequential changes inside the active task with the smallest check that demonstrates the requested behavior.

qinbatista Bundle

Coordinate tasks with clear goals, relevant skills, safe parallel work, and verification before completion.

qinbatista Bundle

Use for requested optimization or an authorized reusable workflow improvement. Preserve intended behavior and measure claimed gains; repetition or shorter prose alone is not a reason to expand scope.

sitabanubanu Bundle

Acquire authorized URL, query, platform, browser-exported, and local source material through Knowledge Workflow's native provider routing and write a validated Acquisition Bundle v2. Use for provider doctor/matrix/route planning, staged acquisition attempts, retries, and provider-neutral source imports; never judge evidence sufficiency or write reports.

victorbuto Skill

Пишет фоллоу-ап по встрече из транскрипта или черновых заметок — плотное саммари на один экран с лид-абзацем, тематическими секциями, Next Steps с владельцами и Decisions Made, готовое к отправке участникам. Использовать когда пользователь просит написать фоллоу-ап встречи, саммари/итоги встречи для отправки, письмо по итогам синка, оформить заметки со встречи. Триггеры — «напиши фоллоу-ап», «фоллоу ап по встрече», «follow-up», «саммари встречи», «итоги встречи», «письмо по итогам», «оформи заметки со встречи», «minutes of meeting». НЕ использовать для анализа исследовательских интервью (qual-interview-analysis, segmentation-interview-analysis) и профилей людей для нетворкинга (person-profile).

ygwa Bundle

Use when running workflow stages, managing feature stage progression, or building context bundles. Triggers on "workflow", "stage", "runStage", "context.build" intents.

ishandutta2007 Skill

Discovers and invokes Awesome AI Skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

ruan-cat Skill

Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

ruan-cat Skill

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

ruan-cat Skill

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

jsuvic Skill

Use after synthesis to dispatch the next ready task from the TASKS.md ledger through one subagent-driven implementation cycle, one task per invocation.

ix-infrastructure Skill

Route to the right Ix skill or command for your task

koreaben777 Bundle

Use when a multi-step task needs a Planner to set scope, route work to already-existing Developer and Review Team Codex App chat tasks or threads in the same project, inspect evidence, and close one bounded review or fixback cycle.

jim60105 Skill

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

philsaxton Skill

Use when orchestrating work across distinct roles, owners, or workspaces, or when a workflow requires independent authorship, implementation, review, or approval.

philsaxton Skill

Use when a proposed contract, specification, or recorded task basis needs a separate pre-implementation review for implementability and verifiability.

philsaxton Bundle

Create, use, and safely clean named temporary task directories in an existing workspace. Use for disposable scratch lifecycle and temporary-file routing, not workspace setup, retained-artifact deletion, or Git branch/worktree cleanup.

squerne Skill

Turn a messy braindump about a project, win, or struggle into a sharp STAR (Situation, Task, Action, Result) interview story, saved to the story bank. Also matches existing stories against a pasted job description. Use when the user brain-dumps a career experience, asks to prepare behavioral interview stories, or asks which stories fit a job.

dddpaul Bundle

Generate professional draw.io diagrams in XML format from architectural descriptions. Use when Claude needs to create visual diagrams for (1) System architecture diagrams, (2) Microservices layouts, (3) Workflow/BPMN diagrams, (4) Network topology, (5) Data flow diagrams, (6) Any visual representation requiring boxes, containers, arrows, and connections. Handles arrow routing, collision avoidance, consistent layouts, and architectural patterns like three-tier, event-driven, and Camunda/Zeebe clusters.

pavelt-papaya Skill

Introduces metrics instrumentation to a .NET Shine service. Creates a feature-specific metrics interface, adds its implementation to the shared metrics class, registers it in DI, and exports the meter in Program.cs. Use this skill immediately and automatically whenever the user says "introduce metrics", "add metrics", "use metrics", "create metrics", "implement metrics", "metrics in code", or asks to instrument or add observability to a Shine service — for example "introduce metrics for repository queue", "add metrics to the media service", "use metrics in code", "create metrics for X". Do not ask for clarification, just execute the workflow.

objectivlabs Skill

Evidence-grounded to-be design (ADRs + design doc) and an implementation orchestration plan (a machine-readable task ledger). Activates when the user asks to design a target state, plan the work, or produce a task plan for a goal.

0pen-sourcer Skill

Read recent email and sort it into what actually needs a reply (use when the user asks what's in their inbox / to triage their email)

legendarylinux Skill

Keep coding work constrained to the user's requested scope. Use when Codex is creating or modifying code, or when the user says "Avoid scope creep." Require Codex to describe and ask permission before doing non-essential improvements or follow-on work that may support the main task, such as opportunistic refactors, adjacent fixes, broader cleanup, extra abstractions, or new deliverables beyond the direct request. Allow normal verification including linting, test execution, and formatting, plus minimal code strictly required to make the requested change function.

legendarylinux Skill

Use whenever a task writes or modifies PHP code, including PHP files, embedded PHP, tests, scripts, endpoints, and PHP code snippets. Do not activate only because a non-PHP task occurs in a project that contains PHP.

legendarylinux Bundle

Coordinate secure, specification-driven projects through hierarchical subagent delegation and durable project records. Use when the user explicitly invokes `$project-manager`. When a substantial project would benefit from this workflow, offer to use it and wait for acceptance; do not activate it for simple work or without a user-supplied project specification.

apizanti-uxr Skill

Status check and meeting prep (/brief). Requires all five MCPs healthy first. Pulls Jira, Calendar, the local daily wiki, and Confluence. Renders a Cursor Canvas. Use when called by daily-rituals /brief.

colindmurray Skill

Check status of background tasks and coding agents — discover running processes, detect stalls, analyze progress, and generate clear reports.

colindmurray Bundle

Use when launching any background process expected to take more than ~5 minutes — coding agents, system commands, disk repairs, test suites, deployments. Pair with check-on-task for status checks. Tasks notify their origin channel on start/complete/fail/die.

naorpeled Skill

Help a contributor prepare a small first open source contribution using the repository's docs, issue labels, and contribution workflow. Use when a user wants to make a safe, well-scoped first pull request.

yorrick Bundle

Use when asked to explain a process with a flowchart, improve a confusing flow diagram, or build an interactive step-by-step process walkthrough. Covers diagram clarity and keyboard usability, not statistical charts or implementing the production workflow being illustrated.

yorrick Bundle

Use when the user asks for a simple, visual status or progress summary of the current task, including how far along it is, percent complete, what is done, in progress, next, deferred, blocked, or connected by dependencies.

adeleempurpled290 Bundle

Use this skill when the user wants to generate, write, or execute Vivado/Vitis TCL scripts for FPGA design flows. This includes creating projects, running synthesis/implementation, programming devices, working with IP Integrator block designs, debug core insertion, constraint management, simulation, and any Vivado automation task. Trigger when the user mentions Vivado, Vitis, FPGA, TCL scripts for hardware design, bitstream generation, XDC constraints, ILA/VIO debug, or any Xilinx/AMD FPGA toolchain task. This skill generates and executes TCL — it does NOT analyze Vivado output or reports. For debug strategy and core configuration decisions use vivado-debug, for timing analysis use vivado-analysis.

glebis Bundle

Task-based evaluation of a real interface — take one job from the JTBD corpus, attempt it step by step as the person who has it, and record where the attempt breaks. Answers "can someone actually complete this?", which inspection and reaction methods do not. Runs a cognitive walkthrough (four questions per step) against a live URL, a prototype, screenshots, or the code, and reports task success against the outcome it was derived from. Use when you have a task and something operable to attempt it on. Triggers on walkthrough, cognitive walkthrough, task analysis, "can a user actually do this", "test this task", "where do people get stuck", "walk through the signup flow", "test this on mobile", "drive it in the browser", "пройди сценарий".