Coding & Dev Tools

outfitter-dev Skill

Trails framework design tenets — the foundational beliefs, promises, primitives, and patterns that govern the framework. Use when evaluating architectural decisions, reviewing feature proposals, checking alignment with framework principles, or when tenets, principles, or design philosophy are mentioned.

outfitter-dev Bundle

Author, update, and manage Trails ADRs. Use when creating new ADRs, promoting drafts to accepted, updating the ADR index, renaming or renumbering ADRs, or when the user mentions ADR, architecture decision, or decision record.

outfitter-dev Skill

Authoritative architectural ruling on a specific Trails framework question — naming choices, vocabulary compliance, pattern fitness, scope decisions. Consults the constitutional hierarchy, decides, and logs. Use when a definitive call is needed or when 'let Clark decide' is the instruction.

outfitter-dev Bundle

Define, execute, and settle durable Trails goals. Use for non-trivial Trails work spanning issues, Graphite branches or stacks, agents, review loops, CI, release or publication gates, or whenever a Trails goal needs an explicit completion horizon, authority boundary, evidence contract, and resumable packet.

outfitter-dev Skill

Big-picture architectural planning and exploration for the Trails framework. Socratic, principle-anchored exploration of features, ADRs, tenets, and horizon planning. Use when planning new capabilities, drafting or revising ADRs, exploring architectural questions, reviewing tenets, or doing horizon planning.

amajorai Skill

Build or migrate a Ryu Companion app with the fixed Ryu App UI v1 vocabulary. Use when an app needs buttons, forms, lists, detail panes, dashboards, empty states, or any visual polish shared with other Ryu apps.

amajorai Skill

Design layered Ryu app and plugin artwork and render it with Icon Composer's iOS 27 material system. Use when creating an app, choosing its visual identity, or replacing catalog icons.

amajorai Skill

Configure Ryu nodes, models, agents, integrations, privacy, and Gateway policy, including organization/team roles, resource access, app grants, scoped secrets, and budgets. Use to inspect effective settings, apply scoped changes, or diagnose access denials.

agentic-in Bundle

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

agentic-in Bundle

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

ysyecust Skill

複数のAIエージェントとタスク集約ワークフローを調整します。複数のワーカーで作業を分配し、エラーを処理し、結果をマージ。

rogerchappel Skill

Unapproved Comma Follow-on

rogerchappel Skill

Fully Approved Coordinated Actions

rogerchappel Skill

Unapproved Sentence Follow-on

rogerchappel Skill

Fully Approved Action List

rogerchappel Skill

Fully Approved Sentences

saml Skill

Writes an implementation plan to `./.plan/YYYY-MM-DD-hh-mm-TITLE.md`, then self-reviews until it passes.

saml Skill

Scans codebase and updates memory files (`AGENTS.md` and `agents/*.md`) with the latest info. This should be triggered automatically every time you scan codebase.

saml Skill

Creates / updates a Makefile with common commands for the project.

saml Skill

Creates an empty plan file: `./.plan/YYYY-MM-DD-hh-mm-TITLE.md`. Trigger this automatically when plan file needs to be created.

saml Skill

Scaffolds a new project.

saml Skill

Gets jira ticket from git branch name.

saml Skill

Reviews an existing plan file and fixes issues until review passes. Use when you've manually edited a plan and want it re-validated.

saml Skill

Writes git commit message.

saml Skill

Finds the latest plan file in `./.plan/` directory (excludes *.review.md and *.fixplan.md). Trigger this automatically when you need to locate the latest plan file.

aqwsde321 Bundle

로컬 TCP 리스닝 포트의 bind 주소, 소유 프로세스, 실행 파일, 작업 디렉터리와 정리 판단을 보여주고, 사용자가 명시적으로 요청한 뒤 해당 사용자 소유 서버 프로세스만 안전하게 종료한다. 로컬 서버·포트 확인, 특정 포트의 PID 확인, 개발 서버 정리 요청에 사용한다.

aqwsde321 Bundle

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

jwiegley Bundle

Fix all issues — no exceptions, no excuses. Fix every finding uncovered during the work, here and now. "Out of scope," "pre-existing," and "follow-up ticket" are not acceptable framings. Fixes go upstream, everything changed gets a real test, and no reward hacking.

jwiegley Bundle

Translate English language text into high quality, accurate Persian (Farsi) text using a team of specialist reviewers

jwiegley Bundle

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, modern APIs, Swift concurrency, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.

jwiegley Bundle

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

jwiegley Bundle

Methodology for cleaning up a transcript file in place -- paragraphs, punctuation, capitalization -- without changing wording or meaning. Use when asked to clean, format, or fix a speech-to-text transcript, correcting technical vocabulary and spoken punctuation while preserving the speaker's words. The `/fix-transcript` command turns it on with the target file as its argument.

lingwei-zheng Bundle

Polish, restructure, translate, or humanize academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from Academic Phrasebank. Use whenever the user asks to polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section, or Chinese academic draft for publication-quality English, or when the user wants an already polished paper to sound less mechanical through a controlled final human-style pass.

gurudevvv Bundle

Start a new project with a spec before code. Two phases: Vision (what/why) then Blueprint (how/order). Use when: user describes a new project idea ("I want to build a bot", "need a site for...", "I want to build", "need a site for", "new project", "start a project", "plan the project", "build me", "let's make"), says /spec-first, or when existing code has no docs/vision/blueprint. Also triggers on Russian: "хочу сделать", "нужен сайт для", "новый проект", "начинаем", "давай спеку", "запускаем". Do NOT use for: reviewing existing specs (use multi-layer-review), debugging, code review, adding features to a project that already has docs/vision.md, or general Q&A.

gurudevvv Bundle

When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much should I charge,' 'my pricing is wrong,' 'pricing page,' 'annual vs monthly,' 'per seat pricing,' or 'should I offer a free plan.' Use this whenever someone is figuring out what to charge or how to structure their plans. For in-app upgrade screens, see paywalls. For offer construction (bonuses, guarantees, value framing, naming) on services/courses/coaching/high-ticket B2B, see offers.

gurudevvv Bundle

Design First