Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Conduct system-level software architecture reviews assessing component coupling, cohesion, SOLID adherence, API contracts, data model design, operational scalability, and prioritized technical debt.
Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.
Launches focused reviewers for correctness, security, architecture, conventions, simplicity, UX, reliability, telemetry, testing, compatibility, and documentation. Supports single-pass reviews or iterative review-and-fix cycles.
Levantamento de atividade de um membro do time (GitHub + JIRA) durante uma sprint. Aceita nome, GitHub username ou parte do nome e opcionalmente o numero da sprint.
Applies a 24-dimension methodology to MSBuild code, pull requests, designs, and architecture. Reviews concerns including ChangeWave discipline, API surface, concurrency, test coverage, SDK integration, evaluation integrity, dependencies, and cross-platform behavior.
Cross-references code with known Oracle and PostgreSQL behavioral differences to identify migration risks. Covers types, empty strings, sorting, timestamps, transactions, planner behavior, and materialized views, including integration test coverage.
Supports reviewing, rewriting, and editing technical documents, including producing review reports. Defines severity levels, findings formats, exclusions, and a final delivery checklist.
Use when asked to review a code change (diff, branch, or PR) for merge readiness and collaborate asynchronously with another agent (often invoked with tony:does-work) that is or will be pushing fixes to the same change. Leaves P0-P findings in a Changelog section, then sleeps in 5-minute checks (up to 4) waiting for the other agent to respond, re-reviewing whenever it does. Triggers: 'review this…
Covers lead scoring, routing, qualification, pipeline stages, and CRM automation. Addresses data hygiene and the systems connecting marketing activity to sales and revenue.
Creates or edits Harbor task tests and grading criteria using Reward Kit. Supports LLM and agent judges and verifiers that produce reward scores.
Guides creating, updating, or superseding RFCs in Luma. Covers deciding whether a change needs an RFC, updating its status, and marking it as superseded or implemented.
Author and manage Architecture Decision Records (ADRs) in docs/specs/. Use when a significant architectural decision needs to be documented.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name