← all publishers

jesse-merhi

@jesse-merhi source repo

44 published skills

  1. Review Guardrails · jesse-merhi
    Manage budgets, scope, findings, consults, provisional fixes, and fixed-point rules for autonomous reviews.
    0 installs
  2. Feedback Hardening · jesse-merhi
    Evidence-backed user corrections or self-detected mistakes revealing reusable agent failures: delegate one systemic-fix recommendation, get approval, then implement it.
    0 installs
  3. Finding Discipline · jesse-merhi
    Confirm actionable review findings, deduplicate root causes, and exclude nits, vague risks, and style notes.
    0 installs
  4. Pr Review Checkout · jesse-merhi
    Review a GitHub PR in VS Code with local diffs, inline comments, navigation, and its worktree preserved.
    0 installs
  5. Review Until Clean · jesse-merhi
    Run authorized native reviews and fixes until two fresh passes are clean.
    0 installs
  6. Writing For Agents · jesse-merhi
    Write agent-facing skills, AGENTS.md, CLAUDE.md, and linked docs with precise behavioral instructions.
    0 installs
  7. Speak Fking English · jesse-merhi
    Run before every final response: make it concise and clear, cut AI tells, re-pitch confusion, and use visuals only when they help.
    0 installs
  8. Model Writing Guides · jesse-merhi
    Select model-specific writing guidance for another skill, including exact coverage checks, same-family fallback, and one task-wide stale-coverage notice.
    0 installs
  9. Typescript Discipline · jesse-merhi
    Write or review TypeScript with shared types, boundary validation, safe narrowing, and verification.
    0 installs
  10. Atlassian Cloudid Jira · jesse-merhi
    Query Jira, JPD, and Confluence through local Rovo Dev MCP, including site IDs, JQL, CQL, and boards.
    0 installs
  11. Frontend UI Validation · jesse-merhi
    Validate web UI with Playwright screenshots, layout checks, responsive states, and reference comparisons.
    0 installs
  12. Reducing Cognitive Load · jesse-merhi
    Review dense, clever, stringly typed, weakly typed, over-abstracted, or hard-to-read code.
    0 installs
  13. Design Technical Diagrams · jesse-merhi
    Create or refine architecture, lifecycle, sequence, trust-boundary, decision, threat-model, SVG, or HTML diagrams that explain system relationships. Do not use technical diagrams as product runtime or UI proof.
    0 installs
  14. Cold Pr Review Until Clean · jesse-merhi
    Repeat fresh cold reviews and fixes until the configured clean stop condition.
    0 installs
  15. Openclaw Stg Test · jesse-merhi
    Publish and inspect temporary OpenClaw Control UI previews through guarded Cloudflare Quick Tunnels and verify with a fresh OpenClaw browser profile.
    0 installs
  16. Clawhub Local Test · jesse-merhi
    Run a guarded local ClawHub test instance with development Convex data refreshed from production.
    0 installs
  17. Openclaw Local Test · jesse-merhi
    Run an isolated local OpenClaw test Gateway using current Codex or Claude login and settings.
    0 installs
  18. Parallel Slice Orchestration · jesse-merhi
    Implement specs with parallel agents, disjoint ownership, integration, and verification.
    0 installs
  19. Improve Codebase Architecture · jesse-merhi
    Review architecture for module depth, interfaces, locality, dependencies, and testability.
    0 installs
  20. Openclaw Pr Readiness · jesse-merhi
    Prepare or assess openclaw/openclaw PRs for exact-head proof, review, CI, and the scoped ClawSweeper gate. Use when publishing, updating, or preparing an OpenClaw PR for review or merge.
    0 installs
  21. Clawsweeper Until Clean · jesse-merhi
    Re-review ClawSweeper PRs until three clean passes and a platinum-or-better label, then make up to three bounded attempts at diamond and explain the ceiling when platinum remains.
    0 installs
  22. Tdd · jesse-merhi
    Build or fix behavior test-first through a red-green-refactor loop when the user requests TDD, test-first work, or integration-style tests.
    0 installs
  23. Design · jesse-merhi
    Route UI design work among production visual design, interaction and motion implementation, read-only motion review, and explicit multi-variant prototyping.
    0 installs
  24. Cleanup · jesse-merhi
    Discover and remove local development artifacts that belong to finished or abandoned work, including worktrees, branches, stashes, processes, watchers, containers, volumes, build outputs, and simulator state. Use when asked to clean up after a task, PR, branch, worktree, or dev environment; not for source-code refactoring or remote resource deletion.
    0 installs
  25. Handoff · jesse-merhi
    Transfer the current work to a fresh full agent session, placing related work beside the current session and unrelated asides separately.
    0 installs
  26. To Spec · jesse-merhi
    Turn a resolved conversation into an Obsidian spec with testing seams and PR delivery shape.
    0 installs
  27. Diagnose · jesse-merhi
    Debug bugs, failing tests, regressions, flakiness, or unexpected behavior with reproducible evidence.
    0 installs
  28. Grilling · jesse-merhi
    Stress-test a plan, decision, or idea through relentless questions and explicit grill requests.
    0 installs
  29. Research · jesse-merhi
    Investigate technical or product questions against primary sources, preserve substantive discoveries in the project Obsidian notes, and return cited conclusions.
    0 installs
  30. Ask Codex · jesse-merhi
    Ask Codex from a non-Codex harness through a full ACP session for an independent answer or explicitly scoped implementation.
    0 installs
  31. Ask Claude · jesse-merhi
    Ask Claude from a non-Claude harness through a full ACP session for an independent answer or explicitly scoped implementation.
    0 installs
  32. Just Do It · jesse-merhi
    Take one well-defined, cohesive change from its current implementation or delivery checkpoint through exact-head code review, proof, CI, and a reviewer-ready PR. Use only when the user explicitly invokes this skill.
    0 installs
  33. Test Audit · jesse-merhi
    Plan and audit test portfolios before creating, changing, or removing tests or test infrastructure; challenge missing, duplicate, brittle, wrongly placed, ownerless, and dangerous coverage.
    0 installs
  34. To Tickets · jesse-merhi
    Turn a plan or spec into tracer-bullet Obsidian tickets with blockers and logical PR groups.
    0 installs
  35. Code Review · jesse-merhi
    Run authorized native and independent fix-and-rerun reviews for a PR, branch, commit, or diff.
    0 installs
  36. Pr Proof Pack · jesse-merhi
    Create or check concise reviewer-visible PR context and practical proof when an authorized workflow publishes an update or prepares it for merge. Lead with what broke and how it is fixed, use actual product screenshots for static UI changes and recordings for motion or manual interaction, keep technical diagrams as separate system explanations, break down large changes by direct-base +LOC and -LOC, and prefer copyable text for textual behavior.
    0 installs
  37. Skill Cleaner · jesse-merhi
    Audit agent skills: loaded roots, duplicate skills, unused skills, prompt-budget costs, compact descriptions.
    0 installs
  38. Cold Pr Review · jesse-merhi
    Cold-review a PR, branch, or feature with neutral context, changed-flow coverage, and actionable findings.
    0 installs
  39. Session Recall · jesse-merhi
    Find prior local Codex or Claude sessions; keep contents local and inspect cards before opening logs.
    0 installs
  40. Grill With Docs · jesse-merhi
    Ground a plan in repo docs, code, Obsidian notes, ADRs, specs, and tickets, then grill its decisions.
    0 installs
  41. Review Flow Map · jesse-merhi
    Map changed runtime flows through contracts and side effects to risks and proving validation.
    0 installs
  42. Pr Rubbish Audit · jesse-merhi
    Audit PR diffs for unrelated artifacts, noisy comments, deletions, generated drift, and stray refactors.
    0 installs
  43. Wait Efficiently · jesse-merhi
    Wait for a command, CI run, subagent, or timed delay by holding one long call instead of polling; report only meaningful state changes.
    0 installs
  44. HTML Explanations · jesse-merhi
    Create standalone HTML for complex explanations, code walkthroughs, plans, reports, diagrams, or research.
    0 installs