sethdford
- 589 skills
- 0 followers
- last month last updated
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Team 2 · sethdfordSpin 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".
- ▌ Scrum 2 · sethdfordRun 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".
- ▌ Verify 2 · sethdfordProve 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", and any request phrased "verify that <function/file/behavior> works", "verify the function …", "run the tests and report the truth", or "check that <X> really does <Y>" — these all mean spawn the verifier agent, not run the tests yourself in the parent.
- ▌ Rl Status 2 · sethdfordShow 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".
- ▌ Tune Agent 2 · sethdfordPropose 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".
- ▌ Aspect Panel 2 · sethdfordRun 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".
- ▌ Cache Report 2 · sethdfordShow 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".
- ▌ Mine Transcripts 2 · sethdford bundleMine 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 Mining Patches 2 · sethdfordApply 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".
- ▌ Eval 2 · sethdfordRun 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".
- ▌ Spec 2 · sethdfordAuthor 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".
- ▌ Ab Test 2 · sethdfordA/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".
- ▌ Best Of N 2 · sethdfordRun 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".
- ▌ Verify UI 2 · sethdfordVerify 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 —
- ▌ Eval Author 2 · sethdfordGenerate 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".
- ▌ Exec Grounded 2 · sethdfordRun 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".
- ▌
- ▌ Migration Strategy 2 · sethdfordSafe schema migrations, backward compatibility, zero-downtime deployments, and rollback strategies.
- ▌ Capacity Planning 2 · sethdfordForecast infrastructure resource needs (compute, storage, network). Model growth scenarios and utilization targets. Use when planning infrastructure investments or optimizing costs.
- ▌ Definition Of Ready 2 · sethdfordDefine 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.
- ▌
- ▌ Compound · sethdford bundleUse 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.
- ▌ Wave Orchestration · sethdford bundleThis 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.
- ▌ Compound Nightly · sethdfordNightly 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).
- ▌
- ▌
- ▌ Write Standard · sethdfordWrite a well-structured standard document with headers, rules, and examples
- ▌
- ▌
- ▌
- ▌
- ▌ Agent Context Wiring · sethdfordWire standards into CLAUDE.md, AGENTS.md, and .cursor/rules/ using references
- ▌ Caretaker · sethdfordRun 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".
- ▌ Diagnose CI Queue · sethdfordUse 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".
- ▌ Eval · sethdfordRun 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".
- ▌ Spec · sethdfordAuthor 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".
- ▌ Team · sethdfordSpin 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".
- ▌ Scrum · sethdfordRun 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".
- ▌ Verify · sethdfordProve 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".
- ▌ Ab Test · sethdfordA/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".
- ▌ Best Of N · sethdfordRun 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".
- ▌ Rl Status · sethdfordShow 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".
- ▌ Verify UI · sethdfordVerify 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 —
- ▌ Tune Agent · sethdfordPropose 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".
- ▌ Eval Author · sethdfordGenerate 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".
- ▌ Aspect Panel · sethdfordRun 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".
- ▌ Cache Report · sethdfordShow 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".
- ▌ Exec Grounded · sethdfordRun 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".
- ▌ Mine Transcripts · sethdford bundleMine 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 Mining Patches · sethdfordApply 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".
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌