jesse-merhi
- 44 skills
- 0 followers
- 4 hours ago last updated
- ▌ Review Guardrails · jesse-merhiManage budgets, scope, findings, consults, provisional fixes, and fixed-point rules for autonomous reviews.
- ▌ Feedback Hardening · jesse-merhiEvidence-backed user corrections or self-detected mistakes revealing reusable agent failures: delegate one systemic-fix recommendation, get approval, then implement it.
- ▌ Finding Discipline · jesse-merhiConfirm actionable review findings, deduplicate root causes, and exclude nits, vague risks, and style notes.
- ▌ Pr Review Checkout · jesse-merhiReview a GitHub PR in VS Code with local diffs, inline comments, navigation, and its worktree preserved.
- ▌ Review Until Clean · jesse-merhiRun authorized native reviews and fixes until two fresh passes are clean.
- ▌ Writing For Agents · jesse-merhiWrite agent-facing skills, AGENTS.md, CLAUDE.md, and linked docs with precise behavioral instructions.
- ▌ Speak Fking English · jesse-merhiRun before every final response: make it concise and clear, cut AI tells, re-pitch confusion, and use visuals only when they help.
- ▌ Model Writing Guides · jesse-merhiSelect model-specific writing guidance for another skill, including exact coverage checks, same-family fallback, and one task-wide stale-coverage notice.
- ▌ Typescript Discipline · jesse-merhiWrite or review TypeScript with shared types, boundary validation, safe narrowing, and verification.
- ▌ Atlassian Cloudid Jira · jesse-merhiQuery Jira, JPD, and Confluence through local Rovo Dev MCP, including site IDs, JQL, CQL, and boards.
- ▌ Frontend UI Validation · jesse-merhiValidate web UI with Playwright screenshots, layout checks, responsive states, and reference comparisons.
- ▌ Reducing Cognitive Load · jesse-merhiReview dense, clever, stringly typed, weakly typed, over-abstracted, or hard-to-read code.
- ▌ Design Technical Diagrams · jesse-merhiCreate 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.
- ▌ Cold Pr Review Until Clean · jesse-merhiRepeat fresh cold reviews and fixes until the configured clean stop condition.
- ▌ Openclaw Stg Test · jesse-merhiPublish and inspect temporary OpenClaw Control UI previews through guarded Cloudflare Quick Tunnels and verify with a fresh OpenClaw browser profile.
- ▌ Clawhub Local Test · jesse-merhiRun a guarded local ClawHub test instance with development Convex data refreshed from production.
- ▌ Openclaw Local Test · jesse-merhiRun an isolated local OpenClaw test Gateway using current Codex or Claude login and settings.
- ▌ Parallel Slice Orchestration · jesse-merhiImplement specs with parallel agents, disjoint ownership, integration, and verification.
- ▌ Improve Codebase Architecture · jesse-merhiReview architecture for module depth, interfaces, locality, dependencies, and testability.
- ▌ Openclaw Pr Readiness · jesse-merhiPrepare 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.
- ▌ Clawsweeper Until Clean · jesse-merhiRe-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.
- ▌ Tdd · jesse-merhiBuild or fix behavior test-first through a red-green-refactor loop when the user requests TDD, test-first work, or integration-style tests.
- ▌ Design · jesse-merhiRoute UI design work among production visual design, interaction and motion implementation, read-only motion review, and explicit multi-variant prototyping.
- ▌ Cleanup · jesse-merhiDiscover 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.
- ▌ Handoff · jesse-merhiTransfer the current work to a fresh full agent session, placing related work beside the current session and unrelated asides separately.
- ▌ To Spec · jesse-merhiTurn a resolved conversation into an Obsidian spec with testing seams and PR delivery shape.
- ▌ Diagnose · jesse-merhiDebug bugs, failing tests, regressions, flakiness, or unexpected behavior with reproducible evidence.
- ▌ Grilling · jesse-merhiStress-test a plan, decision, or idea through relentless questions and explicit grill requests.
- ▌ Research · jesse-merhiInvestigate technical or product questions against primary sources, preserve substantive discoveries in the project Obsidian notes, and return cited conclusions.
- ▌ Ask Codex · jesse-merhiAsk Codex from a non-Codex harness through a full ACP session for an independent answer or explicitly scoped implementation.
- ▌ Ask Claude · jesse-merhiAsk Claude from a non-Claude harness through a full ACP session for an independent answer or explicitly scoped implementation.
- ▌ Just Do It · jesse-merhiTake 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.
- ▌ Test Audit · jesse-merhiPlan and audit test portfolios before creating, changing, or removing tests or test infrastructure; challenge missing, duplicate, brittle, wrongly placed, ownerless, and dangerous coverage.
- ▌ To Tickets · jesse-merhiTurn a plan or spec into tracer-bullet Obsidian tickets with blockers and logical PR groups.
- ▌ Code Review · jesse-merhiRun authorized native and independent fix-and-rerun reviews for a PR, branch, commit, or diff.
- ▌ Pr Proof Pack · jesse-merhiCreate 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.
- ▌ Skill Cleaner · jesse-merhiAudit agent skills: loaded roots, duplicate skills, unused skills, prompt-budget costs, compact descriptions.
- ▌ Cold Pr Review · jesse-merhiCold-review a PR, branch, or feature with neutral context, changed-flow coverage, and actionable findings.
- ▌ Session Recall · jesse-merhiFind prior local Codex or Claude sessions; keep contents local and inspect cards before opening logs.
- ▌ Grill With Docs · jesse-merhiGround a plan in repo docs, code, Obsidian notes, ADRs, specs, and tickets, then grill its decisions.
- ▌ Review Flow Map · jesse-merhiMap changed runtime flows through contracts and side effects to risks and proving validation.
- ▌ Pr Rubbish Audit · jesse-merhiAudit PR diffs for unrelated artifacts, noisy comments, deletions, generated drift, and stray refactors.
- ▌ Wait Efficiently · jesse-merhiWait for a command, CI run, subagent, or timed delay by holding one long call instead of polling; report only meaningful state changes.
- ▌ HTML Explanations · jesse-merhiCreate standalone HTML for complex explanations, code walkthroughs, plans, reports, diagrams, or research.