AGENT SKILLS · MISSION KIT
Useful agent skills ranked by real adoption
Browse verified skills from public repositories. Compare what each skill does, package contents, install activity, and source evidence before adding it to your agent.
- CATALOG SCOPE
- VERIFIED
- skills
- 22,280
- repositories
- 3411
- last synced
- Oct 26, 2026
paulnsorensenage
Review a diff, PR, branch, or path across thirteen dimensions. Emit a severity-grouped findings report. Use when the user wants a code review. Trigger on "review this", "/age", "is this safe to merge", or "find bugs". Also trigger on "spot security issues", "check for slop", "review my PR", or "what's wrong with this code". Review every requested dimension. Review all thirteen dimensions by default. Do not apply fixes. Route them to /cure. Do not harden tests; route that work to /press.
- installs
- 1
- GitHub stars
- 18
- Updated
- Oct 20
paulnsorensenculture
Models problems and trade-offs without writing code or specifications. Use when a workflow needs silent reasoning, or the user asks for "/culture", "no writes", "rubber-duck this", or "these bugs feel connected". Not for specs (/mold), code (/cook), or bug diagnosis and fixes (/pasteurize).
- installs
- 1
- GitHub stars
- 18
- Updated
- Oct 20
paulnsorensenhard-cheese
Checks whether an author can explain a code change before review. Use when the user requests /hard-cheese, /cheese --hard, or an understanding check. Use it before a pull request or through the --hard pipeline flag. Do not use it for reviews, test hardening, or fixes.
- installs
- 1
- GitHub stars
- 18
- Updated
- Oct 20
paulnsorensenmold
Turn a high-leverage design decision into a validated spec through grounded dialogue. Use it when a leverage trigger fires (auth, irreversible effects, concurrency, contracts, destructive ops, a new slice, a cross-slice dependency, an invariant gap) or when the user asks for a spec or design. Typical phrases include "let's design X", "shape this into a spec", "what should the API for Z look like", and "/mold". A feature ask with zero fired triggers is a /cook mini-spec, not a mold; route it thro
- installs
- 1
- GitHub stars
- 18
- Updated
- Oct 20
paulnsorensenplate
Turn finished local work into a commit, an ordinary pull request, or a pull request stack. Use this skill to commit changes or to publish a branch. Use it to open or update a pull request. Use it to create, sync, restack, or submit a pull request stack. You can also run /plate. This skill owns all staging, commits, pushes, pull request creation, and stack changes. GitHub inspection, reviews, comments, CI, issues, releases, and repository administration are outside this skill. Use the gh CLI dire
- installs
- 1
- GitHub stars
- 18
- Updated
- Oct 20
paulnsorensenultracook
Retired — /ultracook no longer exists as a standalone skill. Any /ultracook invocation resolves to /cook, which now owns the single implementation pathway (including the fan-out mechanics this skill used to run). Use /cook instead.
- installs
- 1
- GitHub stars
- 18
- Updated
- Oct 20
paulnsorensenwheypoint
Mark the current conversation as a durable handoff so a new agent can resume the work. Use when the user wants to preserve state for a later or parallel session. Triggers include "hand this off", "write a handoff", "drop a wheypoint", "checkpoint this", "compact the conversation", and "/wheypoint". Also use for "wrap up" or "I need to clear context" during a task. Do NOT use for phase handoffs from /cook, /press, /age, or /cure.
- installs
- 1
- GitHub stars
- 18
- Updated
- Oct 20
renfei-designcontent-review
Review and fix UI text in Figma designs using standard writing style guidelines. Use when asked to review content, fix text, check grammar, capitalization, word choice, or improve UI strings in a Figma design. Extracts text from Figma, reviews against style rules, and applies approved changes back to Figma.
- installs
- 1
- GitHub stars
- 18
- Updated
- Feb 28
renfei-designfigma-slides
Create presentation slides in Figma. Use when asked to create slides, a deck, a presentation, or a pitch in Figma. Builds 1920×1080 slide frames with title, body, key points, and visual references using standard slide layout patterns.
- installs
- 1
- GitHub stars
- 18
- Updated
- Feb 28
curiositechface-recognition-system-builder
Build face recognition systems with InsightFace, ArcFace, enrollment pipelines, HDBSCAN clustering, and privacy-compliant architecture. Activate on: face recognition, face enrollment, face clustering, identity verification, facial search. NOT for: general object detection (computer-vision-pipeline), emotion analysis (ai-engineer).
- installs
- 1
- GitHub stars
- 16
- Updated
- Oct 19
metabaseaudit-architecture
Whole-repo architectural drift sweep. Spawns eight parallel read-only subagents, each focused on one axis across the entire codebase (not just the diff). Aggregates findings into a single severity-ranked report. Use periodically, before milestones, or on user /audit-architecture.
- installs
- 1
- GitHub stars
- 16
- Updated
- Oct 20
heygen-comliveavatar-feedback
Collect and submit developer feedback to the LiveAvatar team. Use when: (1) A LiveAvatar integration is done, working, finished, or complete, (2) The user says "it works", "we're done", "that's it", "ship it", (3) The user is frustrated, stuck, or giving up — "this is broken", "this doesn't work", "I'm stuck", "I give up", "this is frustrating", "I want to report an issue", (4) The user explicitly asks to give feedback, report a bug, file an issue, or share a suggestion about LiveAvatar, (5) You
- installs
- 1
- GitHub stars
- 15
- Updated
- Sep 10
mikonosgtd-harness
GTD skill（兼容包名：gtd-harness）主入口。把任务/承诺转成可信外部系统。 七场景命令：init（搭建/自检）· capture（收集）· clarify（理清）· update（状态更新）· organize（组织）· engage（执行）· review（每周回顾）。 Use when: GTD、任务管理、收集、理清、更新任务状态、完成待办、下一步行动、每周回顾、weekly review、项目组织、清空大脑、session 状态收尾、心如止水、horizons of focus、gtd-harness。 也触发：「帮我把这些待办理一理」「这周该做什么」「我脑子太乱了帮我清空」「搭一个 GTD 系统」。 不触发：纯知识/想法消化（走 fleeting-note → ZK 管线）；具体某条 open loop 的临时记录（旧 open-loops skill 仍可用）。
- installs
- 1
- GitHub stars
- 15
- Updated
- Jun 11
eliasmalmsandberggoogle-ads-segmentation
When the user wants to analyze Google Ads performance by device, geography, day of week, hour of day, or any combination of these dimensions. Also triggers on 'device performance', 'mobile vs desktop', 'bid adjustments', 'geo performance', 'location targeting', 'dayparting', 'ad schedule', 'hourly performance', 'device modifiers', 'geo bid adjustments', 'best time to run ads', 'location exclusions', or 'campaign splits by device or geo'. For full campaign structure see google-ads-search. For Sma
- installs
- 1
- GitHub stars
- 14
- Updated
- Jul 27
jpmorgan-paymentsjpm-integrations-get-started
Triage and credential intake for merchants starting with J.P. Morgan Payments APIs. Use this skill when the user wants to migrate from another payment provider to JPM or start a new JPM integration from scratch. Sets up a .env file (generated fresh or updated in place) with the clientId, certificate path, and private key path that downstream skills will read at runtime. Does not persist credential contents.
- installs
- 1
- GitHub stars
- 13
- Updated
- Oct 20
jpmorgan-paymentsjpm-merchant-integrations
Implement J.P. Morgan Payments API integrations in a merchant project once OAuth authentication is in place. Use this skill after a merchant has completed JPM onboarding and wired up authentication (typically right after jpm-oauth) and is ready to integrate one of the supported APIs — Checkout, Online Payments, Tokenization, 3-D Secure, Account Updater, or Reporting. For inbound webhook handling, use the companion jpm-notifications skill instead. Recommends implementing one API at a time, reusin
- installs
- 1
- GitHub stars
- 13
- Updated
- Oct 20
prasad-vennamandroid-clean-architecture
Use when designing the architecture, data layer, domain models, or business logic for Android apps.
- installs
- 1
- GitHub stars
- 11
- Updated
- Apr 7
prasad-vennamandroid-code-review-expert
Use when performing a code review for Android pull requests, focusing on architecture, memory safety, and UI excellence.
- installs
- 1
- GitHub stars
- 11
- Updated
- Apr 7
prasad-vennamandroid-jetpack-compose
Use when creating, refactoring, or optimizing Android UI components using Jetpack Compose.
- installs
- 1
- GitHub stars
- 11
- Updated
- Apr 7
prasad-vennamandroid-screenshot-testing
Use when implementing visual regression tests, verifying UI layouts, or using Paparazzi/Roborazzi for Android.
- installs
- 1
- GitHub stars
- 11
- Updated
- Apr 7
prasad-vennamandroid-unit-testing
Use when writing or fixing unit tests, mocking objects, or testing reactive flows in Android.
- installs
- 1
- GitHub stars
- 11
- Updated
- Apr 7
pudu-roboticspudu-cloudveil-skill
Use when working with PUDU CloudVeil / 云隐 OpenAPI, SSO, SM2, data board statistics, robot maps, robot status, robot tasks, robot control, callbacks, dispatch, order-to-person, or assets/.openapi.json.
- installs
- 1
- GitHub stars
- 10
- Updated
- May 14
semrushserp-analysis
Analyse the current Google top 10 for one keyword — keyword metrics, search intent, SERP features, the winning content format, and the gap the user can realistically win. Use when the user asks what ranks for a keyword, what the SERP looks like, which format to write, or why competitors outrank them.
- installs
- 1
- GitHub stars
- 9
- Updated
- Oct 20
rolemodelbabysit-pr
Shepherd an already-open pull request to a mergeable state — poll CI, triage review comments, verify each one against the source, push fixes, and keep the branch current. Use when the user asks to "babysit", "monitor", "watch", "shepherd", or "drive" a PR, asks you to "fix the CI on my PR", "handle the review comments", "get this PR green", or "wait for checks and address feedback". Picks up where the create-pr skill leaves off. Does not approve, merge, or close anything.
- installs
- 1
- GitHub stars
- 7
- Updated
- Oct 20