ronniegeraghty
104 verified skills104 total stars
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
testing1
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
testing1
agent-conduct
Shared hard rules enforced across all squad agents
data-ai1
ci-validation-gates
Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22
testing1
.squad/templates/skills/cli-wiring
# Skill: CLI Command Wiring **Bug class:** Commands implemented in `packages/squad-cli/src/cli/commands/` but never routed in `cli-entry.ts`. ## Checklist — Adding a New CLI Command 1. **Create command file** in `packages/squad-cli/src/cli/commands/<name>.ts` - Export a `run<Name>(cwd, options)` async function (or class with static methods for utility modules) 2. **Add routing block** in `packages/squad-cli/src/cli-entry.ts` inside `main()`: ```ts if (cmd === '<name>') {
tools1
contributor-guide
How to contribute, build, test
development1
cross-squad
Coordinating work across multiple Squad instances
tools1
docs-standards
Microsoft Style Guide + Squad-specific documentation patterns
testing1
docs-standards
Microsoft Style Guide + Squad-specific documentation patterns
testing1
economy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
data-ai1
external-comms
PAO workflow for scanning, drafting, and presenting community responses with human review gate
tools1
external-comms
PAO workflow for scanning, drafting, and presenting community responses with human review gate
tools1
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows
data-ai1
github-multi-account
Detect and set up account-locked gh aliases for multi-account GitHub. The AI reads this skill, detects accounts, asks the user which is personal/work, and runs the setup automatically.
data-ai1
git-workflow
Squad branching model: dev-first workflow with insiders preview channel
development1
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
development1
grader-system
Pluggable grader architecture (6 types, gate semantics)
tools1
humanizer
Tone enforcement patterns for external-facing community responses
testing1
humanizer
Tone enforcement patterns for external-facing community responses
testing1
skills/reviewer/java-sdk-validation
# Java SDK Validation Skill You are a **Java Azure SDK validation reviewer** for generated code samples. Your job is to check whether generated Java code follows modern Azure SDK for Java conventions and flag violations of common anti-patterns that LLMs frequently produce. ## Rules 1. **NEVER modify generated code.** You are evaluating, not fixing. 2. Report all findings honestly — pass or fail with specific evidence. 3. Check every rule below. A single violation in a category means that cate
development1
logging-conventions
slog usage, no third-party logging
tools1
model-selection
Determines which LLM model to use for each agent spawn based on 4-layer hierarchy
data-ai1
nap
Context hygiene — compress, prune, archive .squad/ state
tools1
personal-squad
User-level personal agents that travel across projects via Ghost Protocol
data-ai1
process-lifecycle
Session creation, workspace isolation, cleanup
tools1
property-migration
How properties map works, snake_case convention
databases1
reskill
Team-wide charter and history optimization through skill extraction
tools1
reviewer-build
Sets up build environments for generated Azure SDK code samples and attempts to compile/build without modifying generated files. Use during review to verify code compiles correctly.
development1
sdk-version-check
Identifies Azure SDK packages in generated code and checks whether they are the latest available versions. Use during code review to catch outdated dependencies.
development1
secret-handling
Never read .env files or write secrets to .squad/ committed files
documentation1
secret-handling
Never read .env files or write secrets to .squad/ committed files
documentation1
secret-handling
Never read .env files or write secrets to .squad/ committed files
documentation1
squad-conventions
Core conventions and patterns used in the Squad codebase
development1
squad-conventions
Core conventions and patterns used in the Squad codebase
development1
{skill-name}
{what this skill teaches agents}
data-ai1
testing-patterns
Table-driven tests, -race flag, stub patterns
testing1
agent-conduct
Shared hard rules enforced across all squad agents
data-ai1
architectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
development1
ci-validation-gates
Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22
testing1
cli-patterns
Cobra commands in cmd/ package, flag conventions
tools1
client-compatibility
Platform detection and adaptive spawning for CLI vs VS Code vs other surfaces
tools1
config-system
Generator/Reviewer sub-structs, property-based tool filters
tools1
copilot-sdk-integration
How hyoka uses the Copilot SDK
development1
cross-squad
Coordinating work across multiple Squad instances
tools1
distributed-mesh
How to coordinate with squads on different machines using git as transport
tools1
economy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
data-ai1
error-handling
Return errors up, no log-and-return, %w wrapping
tools1
eval-pipeline
How the eval engine works: generate → grade → report
devops1
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
data-ai1
github-multi-account
Detect and set up account-locked gh aliases for multi-account GitHub. The AI reads this skill, detects accounts, asks the user which is personal/work, and runs the setup automatically.
data-ai1
history-hygiene
Record final outcomes to history.md, not intermediate requests or reversed decisions
testing1
init-mode
Team initialization flow (Phase 1 proposal + Phase 2 creation)
tools1
model-selection
Determines which LLM model to use for each agent spawn based on 4-layer hierarchy
data-ai1
personal-squad
User-level personal agents that travel across projects via Ghost Protocol
data-ai1
project-conventions
Core conventions and patterns for this codebase
development1
prompt-authoring
Expert guidance for authoring evaluation prompts for hyoka, the Azure SDK Prompt Evaluation Tool. Use when creating, reviewing, or improving .prompt.md files that test AI agent code generation quality.
tools1
prompt-conventions
Prompt frontmatter format, properties, migration
development1
report-generation
JSON/HTML/Markdown reports, template system
development1
reskill
Team-wide charter and history optimization through skill extraction
tools1
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
tools1
serve-patterns
API endpoints, SPA dashboard, path traversal protection
development1
session-recovery
Find and resume interrupted Copilot CLI sessions using session_store queries
tools1
test-discipline
Update tests when changing APIs — no exceptions
development1
windows-compatibility
Cross-platform path handling and command patterns
tools1
architectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
development1
client-compatibility
Platform detection and adaptive spawning for CLI vs VS Code vs other surfaces
tools1
distributed-mesh
How to coordinate with squads on different machines using git as transport
tools1
docs-standards
Microsoft Style Guide + Squad-specific documentation patterns
testing1
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows
data-ai1
history-hygiene
Record final outcomes to history.md, not intermediate requests or reversed decisions
testing1
init-mode
Team initialization flow (Phase 1 proposal + Phase 2 creation)
tools1
nap
Context hygiene — compress, prune, archive .squad/ state
tools1
project-conventions
Core conventions and patterns for this codebase
development1
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
tools1
session-recovery
Find and resume interrupted Copilot CLI sessions using session_store queries
tools1
test-discipline
Update tests when changing APIs — no exceptions
development1
windows-compatibility
Cross-platform path handling and command patterns
tools1
distributed-mesh
How to coordinate with squads on different machines using git as transport
tools1
release-process
Step-by-step release checklist for Squad — prevents v0.8.22-style disasters
testing1
session-recovery
Find and resume interrupted Copilot CLI sessions using session_store queries
tools1
squad-conventions
Core conventions and patterns used in the Squad codebase
development1
test-discipline
Update tests when changing APIs — no exceptions
development1
windows-compatibility
Cross-platform path handling and command patterns
tools1
architectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
development1
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
development1
client-compatibility
Platform detection and adaptive spawning for CLI vs VS Code vs other surfaces
tools1
external-comms
PAO workflow for scanning, drafting, and presenting community responses with human review gate
tools1
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
testing1
cross-squad
Coordinating work across multiple Squad instances
tools1
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows
data-ai1
economy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
data-ai1
init-mode
Team initialization flow (Phase 1 proposal + Phase 2 creation)
tools1
github-multi-account
Detect and set up account-locked gh aliases for multi-account GitHub. The AI reads this skill, detects accounts, asks the user which is personal/work, and runs the setup automatically.
data-ai1
model-selection
Determines which LLM model to use for each agent spawn based on 4-layer hierarchy
data-ai1
personal-squad
User-level personal agents that travel across projects via Ghost Protocol
data-ai1
project-conventions
Core conventions and patterns for this codebase
development1
nap
Context hygiene — compress, prune, archive .squad/ state
tools1
code-review-comments
Reads generated Azure SDK code files and adds inline review comments without changing any actual code. Use during code review to annotate quality issues, best practices, and suggestions.
development1
agent-conduct
Shared hard rules enforced across all squad agents
data-ai1
history-hygiene
Record final outcomes to history.md, not intermediate requests or reversed decisions
testing1
reskill
Team-wide charter and history optimization through skill extraction
tools1
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
tools1
ci-validation-gates
Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22
testing1
humanizer
Tone enforcement patterns for external-facing community responses
testing1