moberghr

64 mods across 1 repository, 6 stars between them.

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use when a test fails, a runtime error occurs, or a behavioral regression is reported — reproduce first, then fix the root cause within scope.

6 7d ago A 36 tokens original MIT

fix

26

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use when a change stays within 1-3 files and does not need a formal spec (bug fixes, validation tweaks, small config changes) — self-escalates to implement if scope grows.

6 7d ago B 42 tokens original MIT

golden-path-capture

27

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use when you struggle with the same sub-problem 2+ times then find a working approach — captures the failed attempts and the fix as a reusable lesson, no engineer correction required.

6 7d ago B 43 tokens original MIT

handoff

28

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use when context nears limits, before ending a long session with in-progress work, or handing off to a teammate — captures session state into a recovery artifact so a new session resumes cleanly.

6 7d ago A 42 tokens original MIT

implement

29

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Full feature implementation loop orchestrating planning, batching, verification, and review skills.

6 7d ago B 17 tokens original MIT

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use when executing an approved multi-file implementation to ensure each batch compiles, tests, and stays within the approved manifest.

6 7d ago A 29 tokens original MIT

lesson-mining

31

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Mine past session transcripts for durable lesson and memory candidates, applying a reject-by-default rubric — suggest-only, never auto-writes.

6 7d ago A 30 tokens original MIT

lesson-refresh

32

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Audit the lessons stores for staleness — verify cited paths/symbols, triage each lesson Keep/Update/Consolidate/Retire — suggest-only, retirement is always a human decision.

6 7d ago A 44 tokens original MIT

mtk-doctor

33

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Run an MTK install health check (core files, components, hooks, integrity, environment fit) with PASS/WARN/FAIL diagnostics, --json for CI, and --fix for safe auto-repairs.

6 7d ago A 47 tokens original MIT

mtk-setup

34

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

One-stop setup entry point that bootstraps a repo or re-runs architecture audit.

6 7d ago A 22 tokens original MIT

mtk

35

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Unified entry point that routes natural language requests to the right MTK skill.

6 7d ago A 17 tokens original MIT

pr-review-mining

37

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Mine recurring reviewer-feedback phrases from the last N merged PRs and surface them as suggest-only [MINED:feedback] candidates.

6 7d ago A 31 tokens original MIT

pre-commit-review

38

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Fast security-focused review of staged changes before every commit, checking only critical compliance rules.

6 7d ago A 21 tokens original MIT

prior-work-check

39

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use before approving a spec or starting a multi-file implementation to confirm no existing skill, helper, handler, or lesson already covers the proposed work.

6 7d ago A 33 tokens original MIT

promote-lesson

40

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Promote a personal lesson from .claude/lessons/personal.md or Claude Code native memory to the team-wide tasks/lessons.md, rewording for team applicability.

6 7d ago A 42 tokens original MIT

repo-health

41

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Periodic AI-readiness report — scorecard against 12 named assets plus PR review mining from the last N merged PRs.

6 7d ago A 28 tokens original MIT

research-context

42

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use when a decision needs current external/web info (library best-practices, version behavior, migration guidance) rather than local sources — runs grounded web research and returns a cited brief.

6 7d ago A 40 tokens original MIT

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use when the change touches auth, secrets, audited state, audit trails, infrastructure, or external inputs — treat security as a design constraint, not final polish.

6 7d ago A 37 tokens original MIT

setup-audit

44

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Audit the repo to extract architecture principles, or with --merge unify audits from multiple repos into a single team-wide document.

6 7d ago A 27 tokens original MIT

setup-bootstrap

45

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

One-time repo setup that detects tech stack, audits the codebase, pulls coding guidelines, and generates a project-specific CLAUDE.md.

6 7d ago D 30 tokens original MIT

setup-converge

46

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Judges the codebase against the agreed architecture-principles.md/conventions.md and reports drift as graded, read-only work items — never auto-fixes.

6 7d ago B 37 tokens original MIT

setup-refresh

47

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Refresh generated setup artifacts (principles, conventions, detected tools, AGENTS.md, configs, indexes) against codebase drift — proposes diffs for engineer-edited files instead of overwriting.

6 7d ago B 42 tokens original MIT

moberghr/mtk-agent-toolkit

Skill Claude CodeCodex

Use when framework, SDK, or library behavior is unfamiliar or version-sensitive — verify from local authoritative sources (decompiled/SDK code, in-repo docs) before implementing.

6 7d ago A 39 tokens original MIT