claudecodex

craft

Software craftsmanship discipline skills: grill (the interview primitive — walk a design tree one question at a time, facts looked up by subagent rather than asked, no acting until shared understanding), grill-with-docs (that loop applied to vocabulary, against per-repo CONTEXT.md glossaries), diagnose, prototype, tdd, improve-codebase-architecture, grok (stateful multi-session codebase comprehension with supersession-aware understanding records), zoom-out (adapted in part from mattpocock/skills, MIT), infra-review (architecture/security review of Terraform+Atlantis PRs), quiz-me (opt-in active-recall comprehension check after a code explanation), interrogate-model (holistic representability review of a domain model — the legitimate scenarios and personas it cannot express), design-by-stories (design an artifact's shape — schema, template, data model, config — by modeling its actors and user stories first, then deriving the shape from the stories), and lucid-architecture-diagram (drive AWS cloud architecture diagrams in Lucid, including the two silent-failure modes of its API). derive-conventions (derive a repo's unwritten house style from its own code, adjudicate each inferred rule with the human, and write the approved set to CONVENTIONS.md so the review agents stop re-deriving it). wizard (author an interactive bash wizard that walks a human through the steps only they can perform — third-party dashboards, credentials, CI secrets, one-off cutovers — from a hardened template), resolve-conflicts (recover each side's intent from commits, PRs, tickets and NDR heads before resolving a merge, rebase, or jj conflict; detects git vs jj and follows that VCS's own mechanics), and wait-what (user-invoked: re-pitch a message that did not land, in Simplified Technical English using the repo's own vocabulary) — all three adapted from mattpocock/skills, MIT. screen-critique (critique a UI screen design in a fixed order — purpose against its neighbouring screens, then structure,

0 on GitHubby Jacob Hoehlerv0.17.2Apache-2.0updated 2 days agoDeveloper Tools
/

Plugin craft from marketplace jdh-agents in jdh313/jdh-agents. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (19)

  • derive-conventions

    Derives a host repository's unwritten conventions — naming, error-handling shape, docstring format, CLI voice — from its own code, presents each inferred rule with its evidence for accept/edit/reject, and writes the approved set to CONVENTIONS.md so craft's review agents stop re-deriving them every

  • design-by-stories

    Design or redesign an artifact's shape — a schema, template, data model, config format, note type, or API surface — by modeling its actors and user stories first, then deriving the shape from the stories. One fork at a time, human adjudicates every fork. Distinct from interrogate-model (critiques an

  • diagnose

    Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression. Adapted f

  • domain-modeling

    Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an NDR decision that surfaces while modelling. Adapted from mattpocock/skills (MIT, © 2026 Matt Pocock). - Read - Grep - Glob - Write - Edit - Skill

  • grill-with-docs

    Grill a plan against this repo's CONTEXT.md glossary and NDR atoms, sharpen terminology, and update CONTEXT.md inline as decisions crystallise. Use when stress-testing a plan against project vocabulary, locking in a domain term, or surfacing drift between code naming and the glossary. Adapted from m

  • grill

    Grill the user relentlessly about a plan, decision, or idea — one question at a time, walking the design tree until you reach a shared understanding. Use when the user says "grill me", "grill this", "grill me on this plan", or asks to be interviewed hard about something before acting on it. Adapted

  • grok

    Build durable, supersession-aware understanding of a codebase across multiple sessions — grounded in the repo's real sources rather than parametric guesses, explained one subsystem at a time, and persisted as vault records that graduate into CONTEXT.md and NDR atoms. Bash(obsidian-cli *), Write, Rea

  • improve-codebase-architecture

    Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions surfaced via NDR atoms. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

  • infra-review

    Reviews an AWS Terraform pull request whose plans are produced by Atlantis, from a local checkout. This skill should be used when the user runs `/infra-review <pr-number-or-url>`, says "review this terraform PR", "infra review", "review the atlantis plan", "review this infrastructure change", or ask

  • interrogate-model

    Holistic representability review of a domain model taken as a whole — an authorization scheme, permission table, state machine, data model, or tenancy model. Enumerates the legitimate scenarios the model must serve, marks which are unrepresentable or only-via-overreach, surfaces emergent cross-axis

  • lucid-architecture-diagram

    Create, review, or edit AWS cloud architecture diagrams in Lucid (lucidchart) via the Lucid MCP server. This skill should be used when the user mentions Lucid by name, asks to create/edit a cloud architecture diagram, shares a Lucid URL, asks to review or critique an existing architecture diagram, o

  • prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like. Adapted from mattpocock/skills (MIT, © 2026 Matt Pocock). - Read - Grep - Glob - Write - Edit

  • quiz-me

    Opt-in active-recall comprehension check on code or a concept just explained. Predict-then-verify, one question at a time, pitched at the why and the mental model rather than syntax recall. - Read - Grep - Glob - AskUserQuestion

  • resolve-conflicts

    Resolve an in-progress merge, rebase, or jj conflict by recovering each side's original intent before picking a resolution. Detects git vs jj and follows that VCS's own mechanics. Use when the user says "resolve these conflicts", "fix the merge conflicts", "this rebase is conflicted", "jj log shows

  • screen-critique

    Critique a UI screen design — a mockup, a design-tool board, or a built screen — in a fixed order: purpose, then structure, then copy, then consistency. Use when a screen "doesn't feel right", before iterating on a board, or when asked to review or critique a screen's design. - Read - Grep - Glob

  • tdd

    Test-driven development — the red-green loop, done so the tests are worth keeping. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", wants integration tests, or asks for test-first development. Adapted from mattpocock/skills (MIT, © 2026 Matt Pocock). -

  • wait-what

    Re-pitch a message that did not land, with enough context to follow — in Simplified Technical English, using the repo's own vocabulary. Adapted from mattpocock/skills (MIT, © 2026 Matt Pocock).

  • wizard

    Generate an interactive bash wizard that walks a human through the steps only they can perform — provisioning infrastructure, capturing credentials or CI secrets, clicking through an unfamiliar third-party dashboard, or running a one-off migration or cutover. Use when the user says "write me a wizar

  • zoom-out

    Give broader context or a higher-level perspective — map how code fits into the bigger picture. Adapted from mattpocock/skills (MIT, © 2026 Matt Pocock). - Read - Grep - Glob

Subagents (3)

  • comment-reviewer

    Reviews comments and docstrings for accuracy against the code they describe, covering both comments changed by a diff and — the primary case — comments left unchanged while the code beneath them changed. Expands each changed hunk to its enclosing declaration, cross-references the docstring against t

  • copy-reviewer

    Reviews user-facing copy introduced or changed by a diff — CLI output, error messages, help text, prompts, docs headings — against the voice, casing, and terminology the surrounding product already uses. Grounds every finding in an existing string it can cite; proposes replacement wording but never

  • house-style-reviewer

    Reviews a diff or a set of recent edits against the host repository's own unwritten conventions — naming, file placement, error-handling shape, test structure — inferred from CLAUDE.md/AGENTS.md, tool config, and the surrounding code, never from the reviewer's preferences. Reports findings with file

View source on GitHub

More from jdh313/jdh-agents

All 19 plugins →

librarian

claudecodex

Curates, catalogs, retrieves, and maintains your library of notes and knowledge in an Obsidian vault. Workflow-shaped (Capture / Process / Retrieve / Maintain) and agent-mediated (skills draft, agents execute). 19 skills + 4 agents + 6 references, coupled to the vault conventions in ~/Loose Ends/.claude/rules/{wiki.md,catalog.md} and the Templater templates in ~/Loose Ends/Templates/.

19 skills · 4 agents

0

coach

claudecodex

ADHD-friendly productivity coaching: daily planning (/today, /energy), end-of-day capture (/checkin), weekly scheduling (/plan-week) and review (/weekly), life-direction reviews (/review), goal-to-project alignment (/align), project lifecycle (/intake, /breakdown, /reentry, /sunset), idea capture (/spark), brain dump (/dump), task triage (/triage), decision journaling (/decide), and pattern analysis (momentum, overdue-rescue) with adaptive tone calibration

16 skills · 3 agents

0

spec-flow

claudecodex

Personal SDLC scaffolding for AI-assisted development. A lightweight, ephemeral 'contract' between user and AI drives each code change from captured idea to verified done; the durable layer (CLAUDE.md, ndr atoms, README) lives elsewhere. Lifecycle: capture -> draft -> implement -> close.

7 skills · 2 agents

0

pm

claudecodex

PM helpers for team Linear workflows. Skills for a PM-mode planning session (read the real state, slice work into cold-handoff tickets, confirm every write), single-ticket authoring (a short shaping interview, body composed to the shared issue-body spec), the weekly grooming loop (per-person WIP), plan-to-tickets breakdown (assignee-aware), chart-first mapping of efforts too large to plan in one session, questionnaires that pull a blocking decision out of someone else's head, and end-of-cycle retro notes (attribution + Linear-first output). Composes with the linear plugin; ndr and librarian integrations are optional externals.

7 skills

0

shake-tune

claudecodex

Interpret Klippain Shake Tune results for 3D printers: diagnose issues from PNG graphs, explain findings, recommend fixes, and track results over time. Supports belt comparison, input shaper, vibration profile, axes map, and excitation tests.

1 skill · 5 agents

0

compass

claudecodex

A suite of conversational thinking tools — reflect (Socratic mirror, never recommends, always saves), mull (thinking partner, probes AND contributes opinions, saves substantive sessions only), and converge (advisor, leads with a researched recommendation plus confidence % and refines it one question at a time). Plus a paired evaluation track: first-principles (evidence-first interview that produces a signed-off needs map before any option is named) hands off to solution-research (turns that map into a systems-first parallel-research handoff prompt).

5 skills

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

Maintain craft?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins19 plugins