sethdford

Identify and avoid common architectural mistakes. Recognize patterns of failure. Use when reviewing designs or learning from mistakes.

Practice architectural design with structured problems. Time-limited design challenges. Use for skill development, interviews, team exercises.

Reference catalog of proven architecture patterns. Know when to apply each pattern, tradeoffs, and examples. Use as reference when designing systems.

Lead effective architecture reviews. Manage discussions, surface disagreements, build consensus, document decisions. Use when conducting reviews or running architecture forums.

Prepare for architecture interview questions and scenarios. Practice system design, tradeoff discussions, communication. Use for career development and interview readiness.

Conduct comprehensive system architecture evaluation. Assess design quality, technical debt, operational readiness, scalability. Use when auditing existing systems.

Coach engineers on architecture and design. Provide feedback, guide learning, support growth. Use when mentoring junior architects or senior engineers.

Define foundational architecture principles and decision-making rules. Communicate guidelines across organization. Use when establishing architectural standards or updating strategy.

Mine past Claude Code session transcripts (JSONL) to extract user corrections, successful patterns, and recurring failure modes. Proposes diffs against lessons.md and rules/*.md for human review. Triggers on /mine-transcripts, "mine my sessions", "what did I learn this week", "session retro". Use weekly or after a fleet completes.

Run the bounded harness caretaker — deterministic state gather (predictions, verifier gain, agent health, sensors, drift), then triage ONLY what's flagged under a hard authority boundary (files work, never ships changes). Triggers on /caretaker, "run the caretaker", "harness health check".

Apply the diff/patch outputs from a /mine-transcripts run to lessons.md and rules/*.md after human review. Use after running /mine-transcripts and reviewing the proposed diffs. Triggers on /apply-mining-patches, "apply the mining patches", "apply mining run", "approve and apply the trajectory diffs".

Show the RL value-function snapshot for all agents — mean reward, recent trend, anomalies, top tuning candidates. Use weekly to monitor agent quality. Triggers on /rl-status, "agent rewards", "rl status", "which agents are degrading".

Propose a Reflexion-style patch to a specific agent's prompt based on evidence of recurring failures. Use when the same agent makes the same class of mistake twice, when /mine-transcripts surfaces an agent in agent-tuning.md, or when /eval flags a regression on an agent. Triggers on /tune-agent, "tune the X agent", "fix the agent prompt".

A/B test an agent's current prompt against a candidate variant from policy/<agent>/candidates/. Runs both on the same scenarios, aggregates rewards, recommends promotion if candidate beats current by >1 stderr with n≥10. Triggers on /ab-test, "compare prompts", "test the candidate", "is the new prompt better".

Run a panel of 5 specialized verifiers (correctness, edge-case, security, regression, style) in parallel against a change, with confidence-weighted voting. Disagreement (40-60% pass share) escalates to lead. Replaces single-critic for high-stakes review. Triggers on /aspect-panel, "panel review", "multi-aspect verify", "review with multiple critics".

Run an agent N times in parallel against the same prompt, then aggregate via one of 5 modes — critic argmax, USC consistency, confidence-weighted, hybrid, or AggAgent synthesis. Use for high-stakes invocations where you'd rather pay Nx to be sure. Triggers on /best-of-n, "best of n", "run multiple", "give me three options", "synthesize across rollouts".

Protect stated boundaries: decline, defer, and suggest scripts when overload or misalignment appears

Keep voice, facts, and stated preferences consistent across sessions like a digital mirror

Triage messages, draft replies in the user's voice, and flag risk or urgency

Mirror the user's writing style from samples; avoid generic assistant cadence

Session handoffs for future-you: state, blockers, and the next concrete action

Capture decisions with rationale and optional revisit dates for future-you

Track social and cognitive bandwidth; suggest realistic commitments

Deep-work support: batching, interruption scripts, and scope control

Wire standards into CLAUDE.md, AGENTS.md, and .cursor/rules/ using references

Maintain the documentation index to prevent orphaned standards

Write a well-structured standard document with headers, rules, and examples

Design a quality ceremony that drives standards compliance

Run a thorough drift audit to detect standards divergence

Review a PR for standards compliance during code review

Build a project-specific standards enforcement agent

Design PreToolUse/PostToolUse hooks for standards enforcement

Create and maintain Architecture Decision Records (ADRs) in Confluence. Use when documenting technical decisions, architecture choices, technology selections, or when user mentions ADR, architecture decisions, technical choices, or design decisions.

Generate comprehensive API documentation for Confluence from code, OpenAPI specs, or endpoints. Use when documenting REST APIs, GraphQL APIs, or any API endpoints. Creates structured documentation with examples, parameters, responses, and error codes.

Convert Markdown content to Confluence's ADF (Atlassian Document Format) for creating and updating pages. Use when creating Confluence pages from README files, documentation, or any Markdown content. Handles headings, lists, code blocks, tables, links, and more.

Generate comprehensive release notes for Confluence from Jira issues, git commits, and pull requests. Use when preparing releases, creating changelogs, documenting version updates, or when user mentions release notes, changelog, version, or release documentation.

Create well-structured Jira issues from code changes, conversations, or requirements. Use when creating issues, bugs, stories, tasks, or when the user wants to track work in Jira. Analyzes context to generate clear titles, descriptions, and appropriate fields.

Build and optimize JQL (Jira Query Language) queries for searching issues. Use when the user needs to search Jira issues, filter by complex criteria, find specific bugs or features, or when they mention JQL, queries, or searching Jira.

Assist with sprint planning, backlog grooming, story point estimation, and sprint capacity management. Use when planning sprints, estimating work, organizing backlog, or when user mentions sprint planning, velocity, capacity, or story points.

Run a complete SCRUM sprint with all ceremonies — Product Owner authors stories, Tech Lead designs, Scrum Master orchestrates implementers, Verifier+Aspect-Panel guard quality, Sprint Auditor adversarially audits, Retro feeds back to /tune-agent. Triggers on /scrum, "run a sprint", "scrum me this", "ship this with full process".

Mine past Claude Code session transcripts (JSONL) to extract user corrections, successful patterns, and recurring failure modes. Proposes diffs against lessons.md and rules/*.md for human review. Triggers on /mine-transcripts, "mine my sessions", "what did I learn this week", "session retro". Use weekly or after a fleet completes.

Apply the diff/patch outputs from a /mine-transcripts run to lessons.md and rules/*.md after human review. Use after running /mine-transcripts and reviewing the proposed diffs. Triggers on /apply-mining-patches, "apply the mining patches", "apply mining run", "approve and apply the trajectory diffs".

Run a panel of 5 specialized verifiers (correctness, edge-case, security, regression, style) in parallel against a change, with confidence-weighted voting. Disagreement (40-60% pass share) escalates to lead. Replaces single-critic for high-stakes review. Triggers on /aspect-panel, "panel review", "multi-aspect verify", "review with multiple critics".

Show the RL value-function snapshot for all agents — mean reward, recent trend, anomalies, top tuning candidates. Use weekly to monitor agent quality. Triggers on /rl-status, "agent rewards", "rl status", "which agents are degrading".

Propose a Reflexion-style patch to a specific agent's prompt based on evidence of recurring failures. Use when the same agent makes the same class of mistake twice, when /mine-transcripts surfaces an agent in agent-tuning.md, or when /eval flags a regression on an agent. Triggers on /tune-agent, "tune the X agent", "fix the agent prompt".

This skill should be used when the user asks to "orchestrate tasks", "run parallel agents", "wave orchestration", "iterative agent loops", "swarm agents", "coordinate multiple agents", or needs guidance on decomposing complex tasks into parallel workstreams with iterative refinement.

Nightly maintenance for the compound loop — review each project STATE.md, promote only verified lessons to durable rules, keep MEMORY.md under budget, and log a short digest. Conservative and local only — never edits source, never pushes, never messages anyone. Schedule it to run nightly (see Scheduling).

Use when finishing a non-trivial task, fixing a bug, completing a feature, or wrapping up a session and you want the work to make the system smarter next time. Runs the compound loop — consult memory, do the work, verify with an independent subagent (max 3 cycles), then distill only CONFIRMED lessons into STATE.md and memory. Triggers on "compound", "make this stick", "close the loop", or end-of-task wrap-up.

Provides SRE latency optimization advice for Claude API usage. Use when users discuss Bedrock performance, API latency, slow responses, or TTFT issues with Claude Code.