jesse-merhi

59 mods across 2 repositories, 43 stars between them.

pr-proof-pack

26

jesse-merhi/skills

Skill Codex

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…

not rated 4 changed 1mo ago A 84 tokens original MIT

pr-review-checkout

27

jesse-merhi/skills

Skill Codex

Review a GitHub PR in VS Code with local diffs, inline comments, navigation, and its worktree preserved.

not rated 4 2d ago A 29 tokens original MIT

pr-rubbish-audit

28

jesse-merhi/skills

Skill Codex

Audit PR diffs for unrelated artifacts, noisy comments, deletions, generated drift, and stray refactors.

not rated 4 2d ago A 29 tokens original MIT

jesse-merhi/skills

Skill Codex

Review dense, clever, stringly typed, weakly typed, over-abstracted, or hard-to-read code.

not rated 4 changed 1mo ago A 30 tokens original MIT

research

30

jesse-merhi/skills

Skill Codex

Investigate technical or product questions against primary sources, preserve substantive discoveries in the project Obsidian notes, and return cited conclusions.

not rated 4 2d ago A 28 tokens original MIT

review-flow-map

31

jesse-merhi/skills

Skill Codex

Map changed runtime flows through contracts and side effects to risks and proving validation.

not rated 4 2d ago A 19 tokens original MIT

review-guardrails

32

jesse-merhi/skills

Skill Codex

Manage budgets, scope, findings, consults, provisional fixes, and fixed-point rules for autonomous reviews.

not rated 4 changed 1mo ago A 26 tokens original MIT

review-until-clean

33

jesse-merhi/skills

Skill Codex

Run authorized native reviews and fixes until two fresh passes are clean.

not rated 4 changed 1mo ago A 18 tokens original MIT

session-recall

34

jesse-merhi/skills

Skill Codex

Find prior local Codex or Claude sessions; keep contents local and inspect cards before opening logs.

not rated 4 2d ago A 23 tokens original MIT

skill-cleaner

35

jesse-merhi/skills

Skill Codex

Audit agent skills: loaded roots, duplicate skills, unused skills, prompt-budget costs, compact descriptions.

not rated 4 2d ago A 24 tokens original MIT

speak-fking-english

36

jesse-merhi/skills

Skill Codex

Run before every final response: make it concise and clear, cut AI tells, re-pitch confusion, and use visuals only when they help.

not rated 4 changed 1mo ago A 36 tokens original MIT

tdd

37

jesse-merhi/skills

Skill Codex

Build or fix behavior test-first through a red-green-refactor loop when the user requests TDD, test-first work, or integration-style tests.

not rated 4 changed 1mo ago A 32 tokens original MIT

test-audit

38

jesse-merhi/skills

Skill Codex

Plan and audit test portfolios before creating, changing, or removing tests or test infrastructure; challenge missing, duplicate, brittle, wrongly placed, ownerless, and dangerous coverage.

not rated 4 changed 1mo ago A 38 tokens original MIT

to-spec

39

jesse-merhi/skills

Skill Codex

Turn a resolved conversation into an Obsidian spec with testing seams and PR delivery shape.

not rated 4 2d ago A 21 tokens original MIT

to-tickets

40

jesse-merhi/skills

Skill Codex

Turn a plan or spec into tracer-bullet Obsidian tickets with blockers and logical PR groups.

not rated 4 2d ago A 24 tokens original MIT

jesse-merhi/skills

Skill Codex

Write or review TypeScript with shared types, boundary validation, safe narrowing, and verification.

not rated 4 2d ago A 22 tokens original MIT

wait-efficiently

42

jesse-merhi/skills

Skill Codex

Wait for a command, CI run, subagent, or timed delay by holding one long call instead of polling; report only meaningful state changes.

not rated 4 changed 1mo ago A 33 tokens original MIT

writing-for-agents

43

jesse-merhi/skills

Skill Codex

Write agent-facing skills, AGENTS.md, CLAUDE.md, and linked docs with precise behavioral instructions.

not rated 4 changed 1mo ago A 27 tokens original MIT

feedback-hardening

44

jesse-merhi/skills

Skill Codex

Evidence-backed user corrections or self-detected mistakes revealing reusable agent failures: delegate one systemic-fix recommendation, get approval, then implement it.

not rated 4 2d ago A 32 tokens original MIT

jesse-merhi/skills

Skill Claude CodeCodex

Select model-specific writing guidance for another skill, including exact coverage checks, same-family fallback, and one task-wide stale-coverage notice.

not rated 4 2d ago A 32 tokens original MIT

de-slop

47

jesse-merhi/skills

Skill Codex

variants/gpt-6.md.

not rated 4 changed 1mo ago A 0 tokens copy · 100% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: