85121 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

submit-review

Submit a GitHub PR review (approve, request changes, or comment) with explicit user confirmation via a selection UI. Always invoke this instead of calling `gh pr review` directly. Never bypass this with a direct gh command.

thehammer
thehammer
0

portal-open

Open a page in the Carefeed admin portal across environments via Edge/Chrome (driven by webster). Auto-handles login, org/facility switching, and target navigation. ALWAYS invoke this skill before doing any manual browser navigation to a portal page. Use when user asks to "open referral N", "show me REF-1148", "open the portal staging", "navigate to staging", "open that in staging/demo/production", "pull up referral X", or otherwise wants Claude to drive the browser to any Carefeed portal page. Do NOT use open_tab or navigate manually — use this skill instead.

thehammer
thehammer
0

sessions

Search past Claude Code sessions. Find commands, files modified, and context from previous work. Use when user asks "how did we do X", "find that session where", or "what did I work on".

thehammer
thehammer
0

review-prs

Work the PR review queue end-to-end the Perri way — fetch the actionable queue (all buckets including dependabot), gate on CI, triage into trivial/clean/comment/discuss groups, and drive each group to a decision with explicit batch-or-individual approval. Invoke when the user says "review PRs", "let's review", "work the queue", "do PR review", or similar, or when they type /review-prs.

thehammer
thehammer
0

session-context

Load additional coding session context on-demand including calendar, open PRs, recent work, and TODO items. Use when user asks about schedule, pending work, recent activity, or what to work on next. Enables lazy loading to minimize startup tokens.

thehammer
thehammer
0

tmux

Manage Claude Code tmux windows — list windows, enable remote control in a window, create new agent windows, and restart sessions. Use when asked to list windows, enable RC in a window, open a new agent window, or restart a Claude session.

thehammer
thehammer
0

doc

File and manage project documentation — bug reports, feature requests, ideas, notes, todos, and wip folders — in a project's .claude/ directory. Use when asked to file a bug, log a feature request, capture an idea, add a note, create a todo, or start a WIP investigation folder. Also handles listing, transitioning status, initializing structure, and migrating legacy layouts.

thehammer
thehammer
0

Philsquare Permissions

This skill should be used when the user asks to "add permissions to a policy", "create a policy with roles", "set up role permissions", "configure rolePermissions", "use BasePolicy", or when working with Laravel policies that need role-based permission management. Also activate when creating or modifying policies in a project using philsquare/permissions.

philsquare
philsquare
0

solution-architect

Analyze project briefs to resolve architectural ambiguity before tech stack selection. Determines greenfield vs brownfield, platform constraints, integration requirements, scale expectations, and team context. Produces architecture-context.json for downstream skills.

JHaugaard
JHaugaard
0

fip-veterinary-advisor

Evidence-based diagnostic and treatment guidance for Feline Infectious Peritonitis (FIP). Use this skill when working with veterinary cases involving FIP or potential FIP, including (1) Differential diagnosis when clinical signs suggest FIP, (2) Interpreting diagnostic test results and determining next steps, (3) Treatment planning with GS-441524 or other antivirals, (4) Monitoring treatment response and adjusting protocols, (5) Managing relapses or treatment failures, (6) Client communication about prognosis and treatment options, (7) Prevention strategies and multi-cat household management, (8) Cattery breeding decisions after FIP cases, (9) Any questions about FIP diagnosis, treatment, prevention, or management. Also use when encountering mentions of FCoV, feline coronavirus, effusive/non-effusive disease forms, GS-441524, or related veterinary scenarios.

ggwazi
ggwazi
0

constitutional-writer

Extracts and writes project constitutional information from documents (PDF, MD, TXT). Focuses exclusively on identifying principles, values, governance structures, and formatting them into a proper project constitution.

Azeem-2
Azeem-2
0

ansible-role-init

Scaffold a new Ansible role via ansible-galaxy init

jphetphoumy
jphetphoumy
0

ansible-testinfra

Bootstrap minimal testinfra pytest suite for an Ansible role and remind to run via uv

jphetphoumy
jphetphoumy
0

hello-world

Simple prompt that greets the user and confirms Skillstack wiring.

jphetphoumy
jphetphoumy
0

molecule-init

Initialize Molecule testing framework for Ansible roles with Docker-based TDD setup. Use when creating new Ansible roles, setting up molecule scenarios, or when user asks to initialize molecule testing.

jphetphoumy
jphetphoumy
0

skill-builder

This skill exists to create new skills via the bundled CLI workflow.

jphetphoumy
jphetphoumy
0

ansible-fix

ALWAYS use this skill immediately after running 'ansible-galaxy init' to create a new Ansible role. Also use when the user asks to fix ansible-lint errors or when ansible-lint output shows fixable issues like yaml[comments], schema[meta], meta-incorrect, name[play], or role-name[path] violations.

jphetphoumy
jphetphoumy
0

daily-emails

>

christopheryeo
christopheryeo
0

daily-journals

>

christopheryeo
christopheryeo
0

daily-calendars

>

christopheryeo
christopheryeo
0

daily-JIRA

>

christopheryeo
christopheryeo
0

daily-files

>

christopheryeo
christopheryeo
0

daily-work

>

christopheryeo
christopheryeo
0

daily-knowledge

>

christopheryeo
christopheryeo
0

daily-plans

>

christopheryeo
christopheryeo
0

new-proposal

Outline the lightweight process for turning discovery inputs into a first-draft Sentient proposal.

christopheryeo
christopheryeo
0

news-articles-rename

>

christopheryeo
christopheryeo
0

project-pulse-brief

Curate stakeholder-ready pulse briefs that summarize project portfolio updates, risks, and next steps.

christopheryeo
christopheryeo
0

prospect-brief

Generate an executive briefing on a single lead or sales prospect, covering the last 60 days of emails, Google Drive files (including meeting minutes), Google Calendar meetings, and the matching entry in Mary's Lead Gen Log or Donny's Sales Prospects Tracker. Use when Christopher says "brief me on [company/person]", "prospect brief for [X]", "lead brief", "what's happening with [prospect]", or "prep me on [lead]".

christopheryeo
christopheryeo
0

{{name}}

{{description}}

josephkirk
josephkirk
0

Git Version Control

Provides Git version control operations for managing code repositories. Allows agents to check repository status, view commit history, and perform basic Git operations.

josephkirk
josephkirk
0

grill-design

Investigate and pressure-test the design of a non-trivial software feature before implementation. Use when requirements, architecture, integration points, edge cases, compatibility, migrations, rollout, or testing decisions remain uncertain, especially in an existing codebase.

qduc
qduc
0

coordinator

Coordinate complex work by decomposing it, delegating bounded tasks to available workers, managing dependencies and parallelism, validating evidence, and integrating results. Use when the user asks to coordinate, orchestrate, delegate, use subagents or workers, fan work out, or manage work that benefits from supervised parallel or sequential delivery.

qduc
qduc
0

grill-visual

Interrogate a plan or design in the browser — opens a local web page and pushes questions with hand-authored HTML diagrams (decision trees, comparison grids, flows) to it, then reads the answers back. Use when the user wants to be grilled visually or graphically, wants a visual/interactive grilling UI instead of terminal Q&A, or invokes grill-visual.

qduc
qduc
0

cartographer

Work that's too big to hold in one session, planned as a living map of unknowns — named destination, sharp questions, and fog — resolved one at a time, and kept open through implementation so unknowns found mid-build come back to the map instead of into the diff.

qduc
qduc
0

implement-feature

Implement an approved software feature as thin end-to-end slices before hardening individual components. Use when a concrete feature design or implementation plan already exists and the task requires safe incremental implementation in an existing codebase.

qduc
qduc
0

nafv4-concepts

Create and manage NAF v4 (NATO Architecture Framework) / ADMBw Concepts Viewpoints (C1-C8, Cr) in Sparx Enterprise Architect. Use when the user wants to create C1 (Capability Taxonomy), C2 (Enterprise Vision), C3 (Capability Dependencies), C4 (Standard Processes), C5 (Effects), C7 (Performance Parameters), C8 (Planning Assumptions), or Cr (Capability Roadmap) diagrams, add capability elements, create associations between capabilities, enterprises, activities, or work with NAF concepts modeling. Also triggers on natural language like "capability", "enterprise vision", "enduring task", "desired effect", "measure of effectiveness", etc.

carstenlucke
carstenlucke
0

nafv4-architecture-metadata

Create and manage NAF v4 (NATO Architecture Framework) / ADMBw Architecture Foundation/Metadata Viewpoints (A1-A8, Ar) in Sparx Enterprise Architect. Use when the user wants to create A1 (Meta-Data Definitions), A2 (Architecture Products), A3 (Architecture Correspondence), A4 (Methodology Used), A5 (Architecture Status), A6 (Architecture Version), A7 (Architecture Compliance), A8 (Standards), or Ar (Architecture Roadmap) diagrams, add architecture metadata elements, create associations between architecture descriptions, or work with NAF architecture foundation modeling. Also triggers on natural language like "architectural description", "view", "viewpoint", "concern", "standard", "protocol", "architecture correspondence", etc.

carstenlucke
carstenlucke
0

nafv4-assistant

NAF v4 / ADMBw modeling assistant providing convenience functions for common modeling tasks. Offers specialized utilities like requirement naming, batch operations, and modeling helpers. Automatically routes to appropriate function based on user request or allows browsing available functions. Integrates with nafv4-coordinator for all NAF modeling operations.

carstenlucke
carstenlucke
0

nafv4-coordinator

Coordinate NAF v4 / ADMBw modeling across all viewpoint categories. Routes requests to specialized skills (Requirements, Architecture Metadata, Concepts, Logical Specification, Physical Resources, Service Specification) and handles cross-viewpoint relationships. Use when the user wants to work with multiple viewpoint categories, create relationships between different viewpoint types (e.g., Requirement → Capability, Capability → Service), or needs guidance on which viewpoint to use.

carstenlucke
carstenlucke
0

nafv4-physical-resources

Create and manage NAF v4 (NATO Architecture Framework) / ADMBw Physical Resource Specification Viewpoints (P1-P8, Pr) in Sparx Enterprise Architect. Use when the user wants to create P1 (Resource Types), P2 (Resource Structure), P3 (Resource Connectivity), P4 (Resource Functions), P5 (Resource States), P6 (Resource Sequence), P7 (Data Model), P8 (Resource Constraints), or Pr (Configuration Management) diagrams, add resource elements, create associations between resources, or work with NAF physical architecture modeling. Also triggers on natural language like "system", "resource type", "function", "interface", "protocol", "state machine", etc.

carstenlucke
carstenlucke
0

nafv4-service-specification

Create and manage NAF v4 (NATO Architecture Framework) / ADMBw Service Specification Viewpoints (S1-S8, Sr) in Sparx Enterprise Architect. Use when the user wants to create S1 (Service Taxonomy), S2 (Service Structure), S3 (Service Interfaces), S4 (Service Functions), S5 (Service States), S6 (Service Interactions), S7 (Service Interface Parameters), S8 (Service Policy), or Sr (Service Roadmap) diagrams, add service elements, create service interfaces, model service functions, or work with NAF service modeling. Also triggers on natural language like "service specification", "service interface", "service function", "service policy", "service taxonomy", etc.

carstenlucke
carstenlucke
0

nafv4-logical-specification

Create and manage NAF v4 (NATO Architecture Framework) / ADMBw Logical Specification Viewpoints (L1-L8, Lr) in Sparx Enterprise Architect. Use when the user wants to create L1 (Node Types), L2 (Logical Scenario), L3 (Node Interactions), L4 (Logical Activities), L5 (Logical States), L6 (Logical Sequence), L7 (Information Model), L8 (Logical Constraints), or Lr (Lines of Development) diagrams, add logical elements, create flows and interactions, or work with NAF logical architecture modeling. Also triggers on natural language like "operational performer", "logical node", "operational activity", "information exchange", "logical flow", etc.

carstenlucke
carstenlucke
0

nafv4-requirements

Create and manage NAF v4 (NATO Architecture Framework) / ADMBw Requirements Viewpoints (R2-R6) in Sparx Enterprise Architect. Use when the user wants to create R2 (Requirement Catalogue), R3 (Requirement Dependencies), R4 (Requirement Conformance), R5 (Requirement Derivation), or R6 (Requirement Realization) diagrams, add requirements elements, create associations between requirements, or work with NAF requirements modeling. Also triggers on natural language like "functional requirement", "requirement category", "derived from", "conforms to standard", etc.

carstenlucke
carstenlucke
0

api-design

Design RESTful APIs with best practices. Use when creating new endpoints, designing API contracts, or reviewing API structures.

neokn
neokn
0

testing-patterns

Write effective tests with proper structure and coverage. Use when writing unit tests, integration tests, or improving test quality.

neokn
neokn
0

chrome-extension-icons

Search and generate icons for Chrome browser extensions. Automatically downloads SVG icons from Iconify (275,000+ free icons), converts them to required PNG sizes (16x16, 32x32, 48x48, 128x128), and updates manifest.json configuration. Use when the user mentions "extension icon", "browser extension icon", "chrome icon", "add icon to extension", "generate icon for extension", or when working with Chrome extension manifest.json icon setup. Supports color customization, local SVG conversion, and batch generation for multiple projects.

Boulea7
Boulea7
0

expert-panel

ACTIVATE when debugging a skill, analyzing why a prompt isn't working, or stuck on a technical problem. Triggers on "what would the panel say", "let's debug this", "why isn't this working", "convene the panel", or when user expresses confusion about skill behavior.

credentum
credentum
0

Query Supabase Database

Execute PostgreSQL queries against the Supabase database using psql with 1Password credential retrieval

bigandslow
bigandslow
0

GitHub Security Alert Fixer

Systematically analyzes and fixes GitHub CodeQL security alerts with proper documentation and testing

bigandslow
bigandslow
0

Page 1502 of 1703 · 85121 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.