← all publishers

sethdford

@sethdford source repo

567 published skills · page 1 of 6

  1. Definition Of Done 2 · sethdford
    PRD and requirements skill for product managers.
    0
    installs
  2. Migration Strategy 2 · sethdford
    Safe schema migrations, backward compatibility, zero-downtime deployments, and rollback strategies.
    0
    installs
  3. Capacity Planning 2 · sethdford
    Forecast infrastructure resource needs (compute, storage, network). Model growth scenarios and utilization targets. Use when planning infrastructure investments or optimizing costs.
    0
    installs
  4. Definition Of Ready 2 · sethdford
    Define criteria for work to enter development (DoR) to ensure engineering time is spent on well-understood, achievable work. Use when standardizing requirements or reducing rework.
    0
    installs
  5. Change Management 2 · sethdford
    Stakeholder management skill for product managers.
    0
    installs
  6. Compound · sethdford bundle
    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.
    0
    installs
  7. Wave Orchestration · sethdford bundle
    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.
    0
    installs
  8. Compound Nightly · sethdford
    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).
    0
    installs
  9. Drift Audit · sethdford
    Run a thorough drift audit to detect standards divergence
    0
    installs
  10. Hook Design · sethdford
    Design PreToolUse/PostToolUse hooks for standards enforcement
    0
    installs
  11. Write Standard · sethdford
    Write a well-structured standard document with headers, rules, and examples
    0
    installs
  12. Standards Index · sethdford
    Maintain the documentation index to prevent orphaned standards
    0
    installs
  13. Ceremony Design · sethdford
    Design a quality ceremony that drives standards compliance
    0
    installs
  14. Pr Standards Gate · sethdford
    Review a PR for standards compliance during code review
    0
    installs
  15. Enforcement Agent · sethdford
    Build a project-specific standards enforcement agent
    0
    installs
  16. Agent Context Wiring · sethdford
    Wire standards into CLAUDE.md, AGENTS.md, and .cursor/rules/ using references
    0
    installs
  17. Caretaker · sethdford
    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".
    0
    installs
  18. Diagnose CI Queue · sethdford
    Use when multiple PRs are stuck BLOCKED or failing CI. Clusters failures by signature, distinguishes systemic main-line bugs from per-PR content bugs, and dispatches O(root-causes) agents rather than O(PRs). Triggers on /diagnose-ci-queue, "queue is stuck", "PRs blocked", "CI is red", "merge queue jammed".
    0
    installs
  19. Eval · sethdford
    Run evaluations against skills, agents, or rules. Use when the user wants to test that a skill triggers correctly, measure agent output quality, compare prompt variants, or detect regressions. Triggers on /eval, "run evals", "test skill", "benchmark agent".
    0
    installs
  20. Spec · sethdford
    Author a three-file spec (requirements / design / tasks) before non-trivial implementation, then verify the implementation satisfies the spec. Adopts the Kiro spec-driven development pattern. Use for features that span 3+ files, new public APIs, or anything you'd want a human to design-review. Triggers on /spec, "write a spec", "spec this out", "design before build".
    0
    installs
  21. Team · sethdford
    Spin up a native Claude Code Teams fleet to tackle a multi-step task — lead orchestrates, specialists work in parallel worktrees, critic + verifier loop guards quality. Use when the task has 3+ independent sub-tasks, when you need different specialists, or when isolation between concerns is required. Triggers on /team, "spin up a team", "fan out", "fleet this".
    0
    installs
  22. Scrum · sethdford
    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".
    0
    installs
  23. Verify · sethdford
    Prove that work actually behaves correctly by spawning the verifier agent to run the code and capture evidence. Use before claiming a task complete, before commit, when in doubt about whether tests prove the right thing. Triggers on /verify, "prove it works", "verify this", "did the change actually work".
    0
    installs
  24. Ab Test · sethdford
    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".
    0
    installs
  25. Best Of N · sethdford
    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".
    0
    installs
  26. Rl Status · sethdford
    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".
    0
    installs
  27. Verify UI · sethdford
    Verify UI changes by capturing before/after screenshots and asking Claude vision to judge whether the change matches intent and didn't break anything else. Mano-verify pattern (arXiv 2509.17336 —
    0
    installs
  28. Tune Agent · sethdford
    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".
    0
    installs
  29. Eval Author · sethdford
    Generate scenario stubs for /eval against a target agent or skill. Reads recent successful invocations from session transcripts and proposes 5+ scenarios covering happy path, edge cases, and negative cases. Triggers on /eval-author, "author scenarios for X", "create eval scenarios", "generate test cases for the X agent".
    0
    installs
  30. Aspect Panel · sethdford
    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".
    0
    installs
  31. Cache Report · sethdford
    Show prompt cache hit rate trends and flag regressions. Use when user asks about cache performance, asks why sessions feel expensive, or wants to verify cache health. Triggers on /cache-report, "cache hit rate", "cache stats", "is caching working".
    0
    installs
  32. Exec Grounded · sethdford
    Run an agent N times in parallel against a code-change task, with each rollout in its own sandboxed copy of the codebase, scored by ACTUAL test pass rate (not just critic opinion). Use for SWE-bench-style code changes where the test suite is the ground truth. Triggers on /exec-grounded, "execution-grounded", "verify by running tests", "best-of-N with tests".
    0
    installs
  33. Mine Transcripts · sethdford bundle
    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.
    0
    installs
  34. Apply Mining Patches · sethdford
    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".
    0
    installs
  35. Celebration · sethdford bundle
    Celebration
    0
    installs
  36. Negotiation · sethdford bundle
    Negotiation
    0
    installs
  37. Note Taking · sethdford bundle
    Note Taking
    0
    installs
  38. Prototyping · sethdford bundle
    Prototyping
    0
    installs
  39. Habit Design · sethdford bundle
    Habit Design
    0
    installs
  40. Interviewing · sethdford bundle
    Interviewing
    0
    installs
  41. Storytelling · sethdford bundle
    Storytelling
    0
    installs
  42. Apology Craft · sethdford bundle
    Apology Craft
    0
    installs
  43. Brainstorming · sethdford bundle
    Brainstorming
    0
    installs
  44. Grief Support · sethdford bundle
    Grief Support
    0
    installs
  45. Improvisation · sethdford bundle
    Improvisation
    0
    installs
  46. Mental Models · sethdford bundle
    Mental Models
    0
    installs
  47. Moral Courage · sethdford bundle
    Moral Courage
    0
    installs
  48. Team Dynamics · sethdford bundle
    Team Dynamics
    0
    installs
  49. Analogy Engine · sethdford bundle
    Analogy Engine
    0
    installs
  50. Feedback Craft · sethdford bundle
    Feedback Craft
    0
    installs
  51. Growth Mindset · sethdford bundle
    Growth Mindset
    0
    installs
  52. Memory Hygiene · sethdford
    Memory Hygiene
    0
    installs
  53. Meta Cognition · sethdford bundle
    Meta-Cognition
    0
    installs
  54. Prioritization · sethdford bundle
    Prioritization
    0
    installs
  55. Self Awareness · sethdford bundle
    Self-Awareness
    0
    installs
  56. Simplification · sethdford bundle
    Simplification
    0
    installs
  57. Trust Building · sethdford bundle
    Trust Building
    0
    installs
  58. Design Thinking · sethdford bundle
    Design Thinking
    0
    installs
  59. Empathy Mapping · sethdford bundle
    Empathy Mapping
    0
    installs
  60. Paradox Holding · sethdford bundle
    Paradox Holding
    0
    installs
  61. Project Scoping · sethdford bundle
    Project Scoping
    0
    installs
  62. Purpose Finding · sethdford bundle
    Purpose Finding
    0
    installs
  63. Self Regulation · sethdford bundle
    Self-Regulation
    0
    installs
  64. Time Management · sethdford bundle
    Time Management
    0
    installs
  65. Visual Thinking · sethdford bundle
    Visual Thinking
    0
    installs
  66. Active Listening · sethdford bundle
    Active Listening
    0
    installs
  67. Boundary Setting · sethdford bundle
    Boundary Setting
    0
    installs
  68. First Principles · sethdford bundle
    First Principles
    0
    installs
  69. Lateral Thinking · sethdford bundle
    Lateral Thinking
    0
    installs
  70. Nuance Detection · sethdford bundle
    Nuance Detection
    0
    installs
  71. Product Thinking · sethdford bundle
    Product Thinking
    0
    installs
  72. Rapport Building · sethdford bundle
    Rapport Building
    0
    installs
  73. Source Criticism · sethdford
    Source Criticism
    0
    installs
  74. Systems Thinking · sethdford bundle
    Systems Thinking
    0
    installs
  75. Timing Intuition · sethdford bundle
    Timing Intuition
    0
    installs
  76. Critical Thinking · sethdford bundle
    Critical Thinking
    0
    installs
  77. Energy Management · sethdford bundle
    Energy Management
    0
    installs
  78. Ethical Reasoning · sethdford bundle
    Ethical Reasoning
    0
    installs
  79. Feynman Technique · sethdford bundle
    Feynman Technique
    0
    installs
  80. Scenario Planning · sethdford bundle
    Scenario Planning
    0
    installs
  81. Spaced Repetition · sethdford bundle
    Spaced Repetition
    0
    installs
  82. Twin Decision Log · sethdford bundle
    Capture decisions with rationale and optional revisit dates for future-you
    0
    installs
  83. Twin Focus Shield · sethdford bundle
    Deep-work support: batching, interruption scripts, and scope control
    0
    installs
  84. Twin Values Check · sethdford bundle
    Compare plans and drafts against stated values and surface tensions explicitly
    0
    installs
  85. Consensus Building · sethdford bundle
    Consensus Building
    0
    installs
  86. Cultural Awareness · sethdford bundle
    Cultural Awareness
    0
    installs
  87. Decision Framework · sethdford bundle
    Decision Framework
    0
    installs
  88. Explanation Design · sethdford bundle
    Explanation Design
    0
    installs
  89. Financial Literacy · sethdford bundle
    Financial Literacy
    0
    installs
  90. Gratitude Practice · sethdford bundle
    Gratitude Practice
    0
    installs
  91. Hypothesis Testing · sethdford bundle
    Hypothesis Testing
    0
    installs
  92. Perspective Taking · sethdford bundle
    Perspective Taking
    0
    installs
  93. Persuasive Writing · sethdford bundle
    Persuasive Writing
    0
    installs
  94. Research Assistant · sethdford bundle
    Research topics and compile summaries from multiple sources
    0
    installs
  95. Strategic Planning · sethdford bundle
    Strategic Planning
    0
    installs
  96. Temporal Reasoning · sethdford
    Temporal Reasoning
    0
    installs
  97. Twin Energy Budget · sethdford bundle
    Track social and cognitive bandwidth; suggest realistic commitments
    0
    installs
  98. Twin Identity Sync · sethdford bundle
    Keep voice, facts, and stated preferences consistent across sessions like a digital mirror
    0
    installs
  99. Twin Inbox Partner · sethdford bundle
    Triage messages, draft replies in the user's voice, and flag risk or urgency
    0
    installs
  100. Twin Learning Loop · sethdford bundle
    Turn conversations into durable notes, spaced review prompts, and links to active goals
    0
    installs