Adam Johnson
Community@adjohn · PDX
Product Builder. Currently at New Relic, 3x co-founder.
Agent Skills by Adam Johnson
Showing 47 vetted skills indexed across 1 GitHub repositories.
adjohnreproduce-and-fix-issues
Reproduce triaged Slack bug reports through real UI interaction and open verified draft pull requests.
adjohnsetup-benny
Configures Benny's Slack triage and issue-reproduction automations as scheduled Claude Code routines.
adjohntriage-issue-reports
Classify Slack issue reports and post one verdict with tracker dedupe and routing.
adjohnfigure-it-out
Designs an auditable multi-phase playbook for large migrations and ambitious changes.
adjohnbro
Restates the previous AI message in plain language without jargon.
adjohninterrogate
Spawns multiple LLM reviewers to adversarially review code changes and synthesize a verdict.
adjohnprinciple-boundary-discipline
Concentrates validation and error handling at system boundaries while keeping business logic in pure functions.
adjohnsetup-pstack
Configure per-role model assignments for pstack skills in an always-loaded override file.
adjohnswarm
Orchestrates parallel background subagents and aggregates their results into one report.
adjohnprinciple-model-the-domain
Encodes domain logic in data structures instead of scattered conditionals across codebases.
adjohntechnical-writing
Applies Diátaxis, Google style, STE, and Global English rules to technical documentation.
adjohnprinciple-fix-root-causes
Guides debugging by tracing symptoms to root causes instead of applying symptom-level workarounds.
adjohnwhy
Investigate design rationale behind code by querying seven evidence sources in parallel.
adjohnprinciple-encode-lessons-in-structure
Converts recurring corrections into lint rules, runtime checks, and automation scripts.
adjohnhow
Explains codebase architecture and subsystem flows using parallel explorer and critic agents.
adjohnblast-radius
Analyzes what a code change could break beyond the diff and proves safety by running real code.
adjohnprinciple-guard-the-context-window
Routes large payloads to subagents and keeps summaries in the main context window.
adjohnprinciple-subtract-before-you-add
Guides removal of dead code and redundant validators before building new features.
adjohnreflect
Spawns three parallel review subagents over a session transcript to route learnings into skill edits.
adjohnprinciple-foundational-thinking
Guides structural decisions on data structures, scaffolding order, and concurrency before writing logic.
adjohnshow-me-your-work
Maintains an append-only TSV decision log recording choices, evidence, and results for reviewable long-running work.
adjohnprinciple-build-the-lever
Builds codemods, scripts, and generators to automate non-trivial code changes.
adjohnpoteto-mode
Orchestrates engineering tasks through playbooks, principles, subagents, and verified PR workflows.
adjohnprinciple-make-operations-idempotent
Designs state-mutating operations to converge to the same end state across retries and crashes.
Frequently Asked Questions About Adam Johnson
FAQPage SchemaWhat tasks can I accomplish with Adam Johnson's skill collection?▼
You can triage and reproduce Slack-reported bugs, run adversarial multi-model code reviews, analyze blast radius of changes, architect module structure before coding, apply TypeScript best practices, write Diátaxis-structured documentation, and enforce design principles like root-cause fixing and idempotent operations.
Who are these skills designed for?▼
Software engineers and technical leads who want disciplined, verifiable development practices. The collection suits developers doing code review, debugging, migrations, architecture design, and documentation, plus teams running configured Benny triage and repro pipelines for Slack-reported issues.
How do the Benny triage and reproduction skills work in practice?▼
Run setup-benny first to configure Slack, tracker, repository, routing, control, model, and budget settings. Then triage-issue-reports produces thread-only verdicts with dedupe and ticket creation, while reproduce-and-fix-issues verifies bugs through an app-control adapter and opens a bounded draft PR only with before-and-after proof.
What prerequisites or dependencies do these skills require?▼
Most skills are self-contained playbooks and principles requiring no external dependencies. The Benny skills require a configured installation with Slack, issue tracker, and repository access. The why skill discovers available MCPs for evidence sources like source control, observability, and analytics.
Do these skills support parallel or multi-reviewer code analysis?▼
Yes. The interrogate skill runs multiple LLM reviewers challenging changes from independent angles, swarm fans out N parallel workers with a consolidated report, arena spawns competing candidates and grafts the strongest parts, and reflect runs three parallel review subagents over the active transcript.