Coding & Dev Tools

amitsinghom Bundle

Use when preparing a pull request and you want a quality read on the diff, wiring a pre-commit hook or CI step that must fail only on NEW issues, triaging analyzer JSON/SARIF findings, or the user mentions code quality, complexity, changed-line gating, baselines, or SARIF. Runs the privacy-first offline analyzer cqa-analyzer (Python, Go, TypeScript/JS, Java, Kotlin, C#, C/C++, and an experimental Rust pilot) and turns findings into a deterministic pass/fail gate scoped to the lines you changed.

amitsinghom Bundle

Use when the user asks to learn, understand, study, master, or prepare for any topic or skill. Turns the request into a structured learning loop — 80/20 plan, difficulty ladder, justified resources, one-page cheat sheet, escalating one-at-a-time quiz, Feynman teach-back — instead of a one-shot explanation. Enforces retrieval practice and spaced retest of logged weak areas.

meshcode-ai Skill

Survey and questionnaire design — sampling plan, sample-size math, question wording, order and non-response bias checks, analysis-ready instrument. Use when user says "survey design", or needs quantitative validation of a hypothesis.

xxjrq Bundle

读取指定抖音账号的公开可见资料和作品样本，生成有证据、有时间范围、可解释的账号诊断与选题建议。用户要求分析抖音账号、对比近期作品、整理公开数据或制定今日选题时使用；不用于推断后台权重、限流原因或保证增长。

jtaroreh Skill

Clean AI slop and defensiveness out of code and diffs before commit. Strips narrating comments, redundant guards, speculative error handling, unused abstractions, and dead compatibility code.

jtaroreh Skill

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.

jtaroreh Skill

Cut AI tells from any writing. Must always apply.

jtaroreh Bundle

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

jtaroreh Bundle

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.

jtaroreh Skill

Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via unslop, optionally pulling fresh evidence from recent transcripts.

jtaroreh Skill

Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.

openadminos Bundle

Use when the user wants Greybeard to learn the tenant, onboard a new environment, or seed memory with naming conventions, rings, break-glass accounts, and change windows.

openadminos Bundle

Use when the user asks why Intune devices are noncompliant, failing compliance, blocked, in grace period, or need compliance policy triage.

openadminos Bundle

Use when the user asks about license waste, unused seats, duplicate licenses, downgrade candidates, SKU utilization, or Microsoft 365 cost optimization.

openadminos Bundle

Use when the user asks why the tenant is configured a certain way, or wants to record the reason behind a configuration decision.

openadminos Bundle

Use when the user asks what Intune apps, policies, configuration profiles, devices, or groups are assigned, targeted, excluded, conflicting, or missing.

openadminos Bundle

Use when the user needs minimum Microsoft Graph permissions, scope choices, admin-consent notes, over-permissioning review, or least-privilege access planning.

modus-znz Bundle

Kill vibecode: exact names, real error handling, no over-abstraction, edges covered. For any code write, refactor, or review.

modus-znz Skill

Keep the repo maintained: git hygiene, honest commits, behavior tests, CI green. Load when committing or landing work.

modus-znz Bundle

Senior code habits: exact names, why-comments, real error handling, honest types, edges handled. Load when writing or changing code.

modus-znz Skill

Choose like a senior: smallest surface, stdlib-first, boring over clever, measure first. Load when picking architecture or tools.

xxjrq Bundle

将小说内容改编成中文推文或短视频推广方案，输出标题、人物卡、场景卡、口播稿和分镜。适用于章节宣发、书单内容和短剧预告；保留原作事实，不承诺爆款、收益或平台审核结果。

xxjrq Bundle

闲鱼多账号任务工作台。用户需要把多个闲鱼账号的商品草稿、竞品搜索或消息整理按 EasyBR 浏览器环境分组执行时使用。每个账号必须绑定唯一 browserId 和账号别名，同一浏览器串行、不同浏览器可有限并行；默认只读或 draft-only，不自动私信、改价、下架、删除或发布。

xxjrq Bundle

中文去 AI 味和真实写作润色 Skill。把生硬、空泛、模板化的中文改成具体、克制、有生活质感的表达，同时保留事实、数字、专名、原始立场和情绪。Use when the user asks for 中文润色、去 AI 味、自然改写、降低机器腔、自媒体文案润色、职场文字改写、文章诊断或 humanize Chinese writing.

xxjrq Bundle

在多个用户明确指定的 EasyBR 浏览器环境中隔离执行抖音公开内容分析，汇总账号诊断、评论需求洞察和竞品研究结果。用户需要多账号并行检查、统一报告或按账号分组内容建议时使用；不保存登录信息，不自动评论、私信或发布。

jtaroreh Bundle

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

jtaroreh Bundle

Generate a project-local verification skill that drives your app the way a user does across any language, framework, or platform. Use for /create-verification-skill, 'make a control skill for this repo', or when a project has no scripted way to prove UI/CLI/service behavior.

jtaroreh Skill

Apply when handed a problem, constraint, or design you are tempted to accept as given. Ask if the premise is false, the constraint is self-imposed, or a simpler framing eliminates the work entirely.

jtaroreh Skill

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

jtaroreh Skill

Apply when writing or reviewing tests. Test what the system does from the outside (inputs, outputs, observable behavior, invariants), not how it is structured internally (private methods, call counts, internal state).

pgomezurrea-eng Skill

Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

p7th0n Skill

Apply when writing or editing prose meant for humans to read — READMEs, docs, comments, commit messages, PR descriptions, user-facing text. Not for code itself or structured data.

presidenteog Skill

Relentless multi-round interview that resolves every open decision in a plan or design before building starts. Use when the user says "grill me", wants their thinking stress-tested, wants to align before implementing, or is about to start a build from a vague brief. Distinct from loose ideation and from a single clarifying question.

farzammohammadi Skill

Analyze code changes, group them into logical packages where appropriate, to create sequential, clear, descriptive commits with effective titles and detailed descriptions

farzammohammadi Bundle

Analyze code changes, group them into logical packages where appropriate, to create sequential, clear, descriptive commits with effective titles and detailed descriptions

farzammohammadi Bundle

Prepare context handoff for next chat session