mattdurham
38 verified skills289 total stars
team-analyst
Self-directed analyst that claims analysis tasks from a shared task list and writes findings (read-only)
documentation9
team-coder
Self-directed coder that claims tasks from a shared task list and implements them
development9
team-brainstormer
Self-directed brainstormer that claims a brainstorm task, researches the codebase, and stays alive to answer questions from teammates
development9
team-challenger
Self-directed challenger that claims completed analysis tasks and stress-tests them (read-only)
testing9
team-planner
Self-directed planner that claims a plan task (blocked by brainstorm), creates the implementation plan, and stays alive to answer questions from teammates
data-ai9
workflow-implementer
Implements code changes following plans and specifications
development9
team-reviewer
Self-directed reviewer that claims completed tasks and reviews them incrementally
data-ai9
bob:work
Team-based development workflow using experimental agent teams - INIT → WORKTREE → BRAINSTORM → PLAN → EXECUTE → REVIEW → COMPLETE
development9
bob:premortem
Run a premortem — imagine a project has failed and work backwards to identify risks before they happen
data-ai8
bug-finder
Finds bugs in existing code — nil dereferences, race conditions, resource leaks, logic errors, error handling gaps. Creates cleanup tasks for each finding.
development8
workflow-coder
EXECUTE phase coordinator that orchestrates implementation, task review, and code quality subagents
development8
workflow-brainstormer
Autonomous brainstorming agent for workflow orchestration
data-ai8
spec-doc-reviewer
Verifies that SPECS.md, NOTES.md, TESTS.md, BENCHMARKS.md, and documentation cross-reference cleanly against each other and against the actual code
development8
architecture-introspector
Analyzes code for unnecessary complexity, unjustified abstractions, and structural cleanup opportunities using first-principles engineering methodology
development8
bob:postmortem
Write a blameless incident postmortem — gather timeline, root cause, impact, action items
testing8
bob:adversarial-review
Adversarial deep code review — orchestrator spawns 8 specialist agents in parallel hunting spec drift, comment lies, memory hazards, concurrency bugs, contract gaps, code quality issues, and structural over-abstraction. Outputs severity-ranked findings to .bob/state/review.md with a routing recommendation.
development7
commit-agent
Creates commits and pull requests with proper git workflow
data-ai7
bob:internal:writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
development7
talk-to-codex
Have a conversation with Codex about code — ask questions or instruct it to write code, looping until consensus.
development7
workflow-code-quality
Checks Go code for idiomatic patterns, quality, and best practices
development7
workflow-tester
Specialized testing agent for running tests and quality checks
testing7
monitor-agent
Monitors CI/CD checks and PR feedback for workflow orchestration
testing7
Explore
Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns, search code for keywords, or answer questions about the codebase. Can write findings to discovery files.
development7
bob:operational
Multi-repo operational workflow — coordinate code changes across repos, build/deploy, and validate end-to-end. INIT → PLAN → CODE → OPERATE → TEST → COMPLETE
development7
bob:cleanup
Team-based code cleanup workflow - DISCOVER → PLAN → CLEANUP LOOP → COMMIT. Simplifies, removes complexity, fixes documentation. Never introduces new functionality.
development7
workflow-task-reviewer
Validates that implementation accomplishes the requested task
testing7
bob:audit
Verify spec invariants and analyze codebase health — DISCOVER → AUDIT → [ANALYZE → SCORE] → REPORT → COMPLETE
development7
bob:code-review
Code review workflow orchestrator - REVIEW → FIX → TEST → COMMIT → MONITOR
development7
bob:explore
Team-based codebase exploration with adversarial challenge - DISCOVER → ANALYZE → CHALLENGE → DOCUMENT
development7
first-mate
First-mate CLI reference guide for spec lookup and code graph analysis in spec-driven Go projects
tools7
bob:internal:go-coding
Go coding guidelines for production-quality code — pool lifetimes, concurrency safety, numeric type boundaries, error handling, and test discipline
development7
bob:generate-overview
Generate a stylized, self-contained HTML report for any Go codebase element — functions, packages, interfaces, structs, handlers, CLI commands, and more
documentation7
go-presubmit-reviewer
Go-specific pre-submit reviewer targeting patterns that survive generic review but cause problems in production — pool lifetimes, concurrency races, int64/int mismatches, early-stop correctness, spec drift, error handling, and test quality
development7
review-consolidator
Comprehensive multi-domain code reviewer that covers all review concerns in a single pass
development7
bob:stage-prs
Break a large changeset into ordered, reviewable PRs — idempotent, call again to advance the stack after merges
data-ai7
team-spec-oracle
Spec authority agent that scans SPECS.md/NOTES.md/TESTS.md/BENCHMARKS.md, answers invariant questions from teammates, and writes final spec doc updates
testing7
workflow-planner
Specialized planning agent for creating detailed implementation plans
testing7
bob:internal:brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
development7