claude

toolbox

Self-contained agent skills for planning, building, reviewing, and shipping software.

1 on GitHubby Adrianv0.7.0MITupdated 4 days ago
/

Plugin toolbox from marketplace skills in adriancodes/skills. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (32)

  • to-tickets

    Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).

  • implement

    Implement a piece of work based on a spec or set of tickets.

  • implement-task

    Use when a task — a slice from a slices file — needs building. The user asks to "implement task 3", "implement slice 3", "build the next task", or "work through the slices". Also when implementation keeps wandering past its slice's bound, or slices get coded but the slices file never reflects it. ca

  • simplify-code

    Use when the user asks to "simplify this code", "remove the fluff", or wants bloated, superfluous, duplicated, over-abstracted, or dependency-heavy code reduced without changing behavior. category: Quality summary: Condenses scoped code by deleting unjustified concepts while preserving maintainabili

  • be-concise

    Use when the user wants brief, complete-sentence answers: says "tldr", "keep it short", "be brief", or "in plain english", including /be-concise. Also when replies keep arriving as multi-header essays to one-line questions. category: Communication summary: Answer-first layered replies — a short comp

  • build-loop

    Use when an agent should work continuously or on a schedule. The user asks to "build a loop", "set up a self-directed cycle", "run this nightly", or "keep X green/tidy automatically". Also when an existing loop burns tokens, repeats failed fixes, opens duplicate PRs, or ships unreviewed changes. cat

  • code-review

    Use when a user asks to "review this branch", "review this PR", "review my changes", or "review since main". Also use for pre-merge review, work-in-progress diffs, staged changes, suspected regressions in a patch, or checking implementation against a specification. category: Quality summary: Reviews

  • create-skill

    Maintainer workflow for creating, improving, reviewing, and evaluating an agent skill.

  • create-spec

    Use when requirements need pinning down before anything is built: the user asks to "spec this out", "stress-test my design", "poke holes in this plan", or says "write this up as a spec" after a design discussion. Also when a plan is vague, rests on unstated assumptions, or decisions keep getting rel

  • diagnose

    Use when a user asks to "diagnose this bug", "debug this failure", "why is this throwing?", or "investigate this regression". Also use for flaky tests, intermittent failures, incorrect behavior, crashes, hangs, and performance regressions whose cause is unknown. category: Quality summary: Proves an

  • engineering-best-practices

    Use when starting a substantive codebase, making or reviewing a non-trivial code change, or deliberately improving a codebase's architecture. Also use when the user asks to "follow best practices", "start a new application", "review this codebase", or "refactor this codebase", or when architecture i

  • explore-options

    Fan out isolated parallel perspectives on an open-ended decision, then converge on a fit-checked, skimmable shortlist. User-invoked.

  • improve-prompt

    User-invoked shortcut that rewrites a rough ask with visible assumptions and never treats rewriting as authority to execute.

  • quiz-changes

    Use when an engineer wants their understanding of pending changes tested before shipping: the user asks to "quiz me on these changes", "test my knowledge", "do I actually understand this", or wants to check they understand AI-generated code before opening a PR. Also when someone is about to ship cod

  • tdd

    Use when implementing a feature, fixing a known bug, changing application behavior, or altering stored, transformed, migrated, serialized, or externally transmitted data. Also use when a user says "use TDD", "test first", "red-green-refactor", or "add this behavior", and when code is being written b

  • understand-codebase

    Use when the user asks to "understand this codebase", "how does this work?", "trace this feature", or needs onboarding, an architecture explanation, or answers about unfamiliar code. Also use for read-only code-path questions before a change. category: Planning summary: Builds a cited, read-only men

  • verify-work

    Use when an artifact must survive hostile input before shipping: the user asks to "verify this", "is this ready to ship", "test this properly", or "find the loopholes". Also when a shipped artifact failed on an input nobody tried, or when verification so far is a happy-path smoke test. category: Qua

  • build-prototype

    Use when a design question needs a runnable answer before production work: the user asks for a "throwaway prototype", a "spike", a "proof of concept", or to "try both approaches and see". Also when alternatives are being argued from reading code instead of from executed output. category: Engineering

  • check-release

    Use when a finished change is about to be released to users: the user asks "is this safe to release", "go or no-go", "release check", or "what's the rollback plan". Also when a release is planned with no written way to undo it, or includes a database change. category: Verification summary: Reads the

  • create-handoff

    Use when the user asks to "create a handoff", "write up where we are", or "leave this for the next agent". Also when a session is ending or running out of context with work unfinished and someone else must continue it.

  • create-rfc

    Use when something is to be built and how to build it is undecided: the user asks to "write an RFC", "which approach should we take", or "should we use X or Y". Also when two or more workable routes would produce different systems and one is about to be picked without weighing them. category: Planni

  • write-pr-description

    Draft or revise a standard pull-request description from the current repository's PR template and actual branch changes. Use when asked to write, generate, prepare, update, or improve a PR body, pull-request summary, testing notes, reviewer context, or checklist for a code change.

  • diagnose-difficult-bugs

    Systematically diagnose complex software defects using evidence preservation, reproduction, causal tracing, ranked hypotheses, and discriminating experiments. Use for intermittent or nondeterministic failures, production-only bugs, regressions, race conditions, memory or performance pathologies, dis

  • deployment-safety

    Assess, plan, execute, and verify safe software deployments and releases. Use for production or staging rollouts, release readiness reviews, deployment checklists, migrations, feature-flag launches, hotfixes, rollback planning, canaries, incident-prone changes, and requests to deploy or validate a d

  • verifying-regression-tests

    Explicitly invoked when a user asks whether existing tests would catch a reported bug if it returned, whether a regression is covered, or requests a clean-versus-bug-restored test comparison.

  • gather-requirements

    Use when a user asks for something to be built and the request leaves out who it is for, why, what done looks like, or its limits: "build me an app that…", "I want to add a feature", "interview me first", or "ask me what you need to know". Also when work is about to start on guessed requirements. ca

  • map-decisions

    Map a project's settled, unanswered, and unspecified decisions across bounded workstreams and sessions.

  • prepare-pr

    Use when the user asks to "prepare my PR", "write a PR title and body", "open a PR for this branch", or "make a local PR draft" from an existing change. Also when a branch needs a description that follows the repository template.

  • research-question

    Use when a decision depends on an external fact that needs sources: the user asks "does version X support Y", "what do the docs actually say", or "find a source for this claim". Also when sources conflict or documentation may describe a different version than the one installed. Excludes quick facts

  • review-code

    Use when a user asks to "review this branch", "review this PR", "review my changes", or "review since main". Also use when asked whether a branch, PR, or diff is ready to merge or ship, and for work-in-progress diffs, staged changes, suspected regressions in a patch, or checking implementation again

  • review-session

    Review an agent session for evidence-backed friction and the smallest measurable remedies.

  • write-agent-instructions

    Make the smallest evidence-backed change to persistent project instructions and test downstream behavior.

Subagents (1)

  • evidence-led-reviewer

    Staff engineer who reviews a bounded change for concrete defects and reports only findings that survive falsification.

View source on GitHub

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

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Maintain toolbox?

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 pluginslisted