Productivity

qf-studio Bundle

Divergent solving for a declared contradiction ("improving X worsens Y"). Produces three competing candidates from different TRIZ separation modes, each with cost and downside, then recommends one. Auto-invoke when user says "find a better solution", "alternatives for", "resolve the contradiction", "triz this", or when a nav-brief declares a Contradiction on a substantial task.

qf-studio Bundle

Render a one-screen intent brief (Goal/Scope/Approach/Limits/Verify/Won't-do/Contradiction) before implementing ambiguous task-shaped prompts, triggered by the prompt_brief op (UserPromptSubmit via hooks/nav_dispatch.py). Confirms scope with max 2 open questions before touching files; detects brief drift mid-task.

qf-studio Bundle

Unified workflow orchestration for substantial tasks. Auto-detects complexity, defers to matching skills, or provides phase-based execution. Solves workflow conflicts between skills, loop mode, and CLAUDE.md.

letsloose501 Bundle

Files a raw meeting transcript as a dated note. Use when a transcript is pasted in, when the user asks to file meeting notes, or when they say the notes have to be tidied before they go into the vault.

letsloose501 Skill

Books a meeting room, checks catering availability, and emails the attendee list to reception before a workshop starts.

insightfulanalytics Bundle

Round-trip TOOLING for Deneb specs in PBIR. Extract/embed the Vega/Vega-Lite spec in visual.json and offline-render it (Vega→PNG/SVG) to verify without Power BI. Use whenever a task touches a Deneb visual's spec ("edit the Deneb visual", "change the Vega spec", "fix the Deneb chart", patching jsonSpec in visual.json), or when a Deneb spec needs rendering/verification without Power BI. Also audits a visual's Deneb build stamp, 2.0-only properties and container signal names, and migrates pbiContainer* / denebContainer references in place. Replaces the ad-hoc inline python patch scripts and per-session npm installs used previously. Spec authoring rules, theme colors, and interactivity live in the custom-visuals:deneb-visuals skill.

scriptedalchemy Bundle

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for $arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

scriptedalchemy Bundle

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for $figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

hyperdargo Skill

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite (default), full, ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

lmaick Skill

Protocolo obrigatório de finalização e entrega para todo worker do Orca no MeuPlantão. Exige ciclo Git completo, publicação de relatório estruturado diretamente no card do Linear e resposta de exatamente 1 linha no terminal para economia de tokens.

wycats Skill

Use when running a prepare-execute-review (PER) cycle, doing a PER workflow, or coordinating work through `prepare`, `execute`, and `review` subagents with explicit gates.

l3rowniecakez Skill

Implement a Redmine UR (User Request) code fix in any Delphi7 group-insurance program suite repo (OGL_Operation, OGL_Claim, OGL_Benefit, OGL_Center_Report, OGL_FindInfo, OGL_Premium, OGL_Reinsurance, OGL_Sale, GroupLife, etc. — not limited to OGL_Operation): read + analyze the RM, plan (with Phase/Task breakdown for large work), get developer approval before any coding, implement phase-by-phase with a review gate at each phase, then record the result as DB script file(s) + a FormEdit.txt update in the ticket folder. Use when user says "/redmine-ur", sends a Redmine UR ticket, or asks to fix/แก้ไข a program point in this suite. Never write code before explicit approval, never touch anything outside the requested scope, and never skip the FormEdit.txt/db-script recording step when a fix is done.

l3rowniecakez Skill

Investigate and answer questions using the SIT environment's Kibana logs. Use when user says '/log-kibana-sit', asks to check Kibana log on SIT, or needs to find/verify something (task status, ESB errors, whether a schedule ran, whether a user did X) from SIT application logs.

yogiraja Skill

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

yogiraja Skill

Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.

matthewye Skill

Run the Distill requirement-to-issues workflow through the installed toolkit CLI.

matthewye Bundle

Autopilot task reviewer. Four-axis review: Behavior alignment, TDD discipline, code quality, plan fidelity. Read-only.

yogiraja Bundle

Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.

matthewye Skill

Run the Distill requirement-to-issues workflow in Kimi through the installed toolkit CLI.

matthewye Skill

Run the Distill requirement-to-issues workflow in Codex through the installed toolkit CLI.

matthewye Skill

Autopilot task reviewer. Five-axis review: Behavior alignment, TDD discipline, code quality (including upstream code-review Fowler baseline), plan fidelity, and upstream code-review consolidation. Read-only.

matthewye Skill

Run the Distill requirement-to-issues workflow in Reasonix through the installed toolkit CLI.

l3rowniecakez Skill

[core] v26.5.16 L-SKLL | Clone or create repos for active development — the right hand of /learn. Workflow modes — default (long-term dev), --flash (issue → PR → offload), --contribute (fork + multi-PR). Use when user says "incubate [repo]", "work on [repo]", "clone for dev", or wants to set up a dev workflow. Do NOT trigger for study/exploration (use /learn), finding projects (use /trace), or session mining (use /dig).

matthewye Skill

Autopilot task reviewer. Five-axis review: Behavior alignment, TDD discipline, code quality (including upstream code-review Fowler baseline), plan fidelity, and upstream code-review consolidation. Read-only.

tommyducx Bundle

ego-browser (ego-lite) is a Chromium-based browser designed from the ground up to be friendly to both human users and AI Agents. AI Agents work in their own isolated space, reusing the user's login state without competing for the browser. Use this skill whenever the user needs to interact with a website opening pages, filling forms, clicking buttons, taking screenshots, extracting page data, testing web apps, logging into sites, automating browser operations, or any other browser automation task. Triggers include requests to "open a website", "visit a URL", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "extract content from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also used for exploratory testing, dogfooding, QA, bug hunting, or reviewing app quality. Prefer ego-browser over any built-in browser automation, web fetch, or other web tools.

arozumenko Bundle

Use when the user asks to 'check my email/Teams/calendar', 'what meetings do I have', 'any messages about X', or whenever a task needs live Microsoft 365 data rather than memory. Microsoft 365 (Graph) access to email, Teams, calendar, and SharePoint — scriptable scans plus an interactive query.py.

arozumenko Bundle

Use when the user says 'save to vault', 'log this note', 'find my notes about X', 'what's in my inbox', 'open loops', or when filing an incoming signal (email/chat/memo) or updating people/project/meeting notes. Headless, file-system Obsidian vault operations, no Obsidian app needed.

arozumenko Bundle

Use when the user says "plan a feature", "design this", "how should we build", or before writing code for any non-trivial feature. Produces an approved task breakdown before implementation begins — plan first, build second.

arozumenko Bundle

Use when the user says "plan a feature", "design this", "how should we build", or before writing code for any non-trivial feature. Produces an approved task breakdown before implementation begins — plan first, build second.

arozumenko Bundle

Use when the user says 'what do we know about X', 'find prior discussions with Y', or before drafting any reply where prior history matters. Gathers cross-channel context (local KB, email, Teams, optional web) about a person or topic before responding.

arozumenko Bundle

Use when the user asks to 'verify', 'did this actually work', 'is X really done' — or before you claim a task is complete and before closing an issue or merging a PR. Goal-backward verification — checks whether the desired outcome was achieved, not whether tasks were marked done.

arozumenko Bundle

Use when a routed task has been implemented and the working code needs to be committed, pushed, PR'd, commented on the issue, and handed to a reviewer. The canonical task-handoff protocol; runs standalone or as the final phase of implement-feature.

arozumenko Bundle

Use when the user says "fix bug", "fix

insideto27 Bundle

Clarify a project with a bounded grill-me-style interview, agree on engineering depth, and coordinate the smallest useful Codex team with completion reports. Use when the user wants a project commander, reusable sidebar agents, cross-task team coordination, or interview-to-execution workflow; also for 总指挥、组建团队、侧边栏代理、跨任务协作、先问清需求再执行.

insideto27 Bundle

Develop or optimize a complete Amazon listing from product, competitor, keyword, VOC, and performance evidence, automatically invoking relevant Amazon specialist skills and delivering a versioned candidate. Use for end-to-end new listing development, substantial or iterative listing optimization, and Feishu listing delivery.

swyxio Bundle

Diagnose or improve tests as a system, including flaky or nondeterministic suites, duplicated coverage, expensive fixtures, slow feedback, and test selection. Use only when the user explicitly makes test architecture or suite behavior the primary task. Do not trigger for ordinary implementation work, adding or fixing a regression test, resolving one product bug, or running existing checks.