Bryan Mendoza's skills help an AI agent work through software engineering tasks end to end, from fetching Jira tickets and GitHub issues into local snapshots, to planning and executing individual tracker tasks, creating child issues or subtasks, and reviewing the recent state of a Git repository. His most popular skills also cover clean code practices and API security, such as authentication, input validation, and rate limiting. Across them, the work stands out for its structured, phase-by-phase workflow that keeps the agent's actions traceable to tracker items and local documentation.
Agent Skills
35 skills · 3 stars
Analyzing Recent Project State Produces a verified, read-only snapshot of a repository's recent state from local Git evidence: w…
Api Security Best Practices Implement secure API design patterns including authentication, authorization, input validation, r…
Clarifying Assumptions Runs the conversational clarification layer for workflow orchestration.
Clean Code This skill embodies the principles of \"Clean Code\" by Robert C.
Code Review Excellence Master effective code review practices to provide constructive feedback, catch bugs early, and fo…
Committing Scoped Changes Creates reviewable atomic git commits from an explicit list of files or folders after the user as…
Council Of Advisors Runs a structured nine-seat council deliberation on an idea, project, business, startup, goal, or…
Creating Work Item Children Creates or reconciles GitHub child task issues or Jira subtasks from an approved Phase 4 task pla…
Diagnosing Root Causes Diagnoses runtime bugs, crashes, regressions, failing CI/CD pipelines, and underspecified user re…
Executing Work Item Task Executes exactly one planned Jira or GitHub work-item task after critique approval.
Fetching Work Item Retrieves a Jira ticket or a GitHub issue into docs/<KEY>.md as a read-only, validated Markdown s…
Generate Flow Diagram Creates, refines, repairs, or decomposes Markdown plus Mermaid workflow diagrams (flowchart or st…
Generate Handoff Document Generates or updates a resumable cold-start handoff package from an in-progress conversation, rev…
Improving Skill Definition Adversarially audits and improves existing first-party agent-skill packages through approval-gate…
Improving Test Suites Improve existing test suites into minimal, high-signal behavior-focused harnesses with approval-b…
Orchestrating Workflow Coordinate an end-to-end Jira or GitHub work-item workflow from initial fetch through per-task im…
Planning Codebase Restructuring Plan a codebase restructuring through read-only architecture mapping, DDD and Screaming Architect…
Planning Task Execution Plans how to execute exactly one already-selected numbered Jira or GitHub task by producing an ex…
Planning Work Item Tasks Plans a Phase 1 Jira ticket or GitHub issue snapshot into staged, validated Phase 2 task-plan art…
Ponytail Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human un…
Pr Creator Create review-ready pull requests or merge requests from the current branch through a fork-aware,…
Prompt Structurer Convert prose prompts into compact, structured XML prompt contracts through staged passes.
Recency Guard Validates answers that depend on current external facts, including prices, versions, policies, ra…
Refactoring Code Coordinates consent-gated, evidence-isolated, behavior-preserving simplification refactors.
Refine Task Review one Jira or GitHub work item for implementation readiness and produce one tracker-facing r…
Reporting Skill Issues Reports observed defects and explicit improvement requests from runs of b-mendoza/agent-skills.
Responding To Pr Review Comments Assess and respond to pull request review comments through a status-gated workflow: collect comme…
Review Pull Request Review one pull request through a standalone, progressively disclosed workflow.
Review Pull Request Reviews one GitHub pull request and prepares a verified local review or posts its exact approved…
Review Software Engineer Cv Reviews and tailors a software engineer CV or resume against a job posting.
Rewriting Code Strictly Rewrite existing Python, TypeScript/JavaScript, or Go code for strict static typing, boundary val…
Stop Slop Remove AI writing patterns from prose.
Unslop Cut AI tells from any writing.
Validate Implementation Plan Audits an implementation plan for requirements traceability, avoidable complexity, risky assumpti…
Workflow Skill Architect Converts repeatable workflows, existing prompts, or skill packages into portable agent-skill arti…