Dev Hooks
claudePolyglot dev-workflow hooks (lint on edit, verification before stopping, a dangerous-command and secret guard, advisory reminders) plus the skills those hooks point at.
25 skills · hooks
Skills for thinking a task through and checking the result: adversarial critique, planning checks, decision records, and verification before claiming done.
Plugin thinking-tools from marketplace dev-hooks in mickzijdel/dev-hooks. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
adrUse the moment a significant technical decision with real trade-offs lands (library, pattern, database strategy, auth, deployment model), without waiting to be asked. Triggers on "record this decision", "why did we choose X", "document our approach to Y", "write an ADR".
automation-reviewUse for the daily automation review the scheduled task runs, or when asked "what should I automate", what repeated work to turn into a skill, hook or tool, or for a look back at recent activity.
boardUse for hard, independent critique of an idea, plan, design, draft, pitch or landing page, and unprompted before returning a consequential plan or draft. Triggers on "poke holes in this", "what am I missing", "be brutal", "convince me this is wrong", or a call needing several expert angles.
brief-backUse at the start of any task the person hands you (research, a doc, code, a plan, a buying decision) to agree depth and done-when, and when they say "be thorough", "quick look", "go deep", or change the scope mid-task. Skip plain questions and lookups.
but-for-realUse when about to claim something is done, fixed, passing or ready to ship, when a change was only eyeballed or pattern-matched and never run, or when the user says "but for real", "for real this time", "don't guess" or "did you actually test it".
code-simplifierSimplify and refine code for clarity, consistency, and maintainability while preserving all functionality. Use after modifying code, when asked to simplify or clean up code, or during refactoring. Focuses on recently changed sections unless directed otherwise.
codebase-designUse when designing or restructuring a module's interface or seam, or judging whether an abstraction earns its keep. Triggers on "design this interface", "is this abstraction worth it", "where should this boundary go", "make this more testable", or another skill needing the deep-module vocabulary.
commit-digestUse weekly, on demand or as a scheduled agent to scan tracked external repos (dotfiles, frameworks), feeds and curated pages for ideas worth pulling into this project. Triggers on "check for new ideas", "what changed upstream", "any improvements to pull in from <repo>", "review dotfiles commits".
domain-modelingUse to build or sharpen a project's CONTEXT.md glossary, resolve vague or conflicting terms, or when another skill needs the domain model maintained. Triggers on "ubiquitous language", "domain glossary", "what should we call this", "add this to CONTEXT.md", or a term that clashes with the glossary.
grillUse to interrogate a plan, design or idea one question at a time until every decision is resolved: \"grill me\", \"interview me\", \"ask me questions about this\", \"stress-test this plan with me\", \"help me fully specify this\", or before writing a plan or PRD from a fuzzy idea. Not for critique (
premortemUse before committing to or starting a non-trivial plan, design, migration, launch or hard-to-reverse decision, above all when optimism runs high and nobody has said what could go wrong, or when asked to stress-test, pressure-test or sanity-check an approach.
retroFlag that this session went badly, with the user's note, for the automation review to diagnose later. Runs only when the user types /retro.
self-rateUse before returning a draft, answer, plan, or code change you're unsure about, or when the user asks how confident you are, how good it is, or to grade/score/critique your own work. Triggers when claims may be overstated, when output quality is uncertain, or when you want to catch weak spots before
the-algorithmUse before the first edit of a change that is not fully specified (a feature, a fix with open choices, a new prompt, hook, process or doc), and when a request piles on requirements, options or steps. Triggers on "run the algorithm", "question the requirements", "what can we delete", "Musk's algorith
thinking-toolboxUse when the user is choosing what to work on, planning, brainstorming, weighing a decision, stuck, avoiding a task, overcommitted, relying on a surprising claim, handling a crisis or a tense group situation, building something for other people, trying to build a habit, or reviewing how they work. C
wait-whatUse when the person seems lost after your last answer: "wait what", "huh?", "I don't follow", "what do you mean", "explain that simpler", or a reply that shows they missed the point. Re-pitch the answer in plain words.
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/thinking-tools-reminder.sh"
Polyglot dev-workflow hooks (lint on edit, verification before stopping, a dangerous-command and secret guard, advisory reminders) plus the skills those hooks point at.
25 skills · hooks
Writing skills: READMEs, plain readable prose, stripping AI tells, and drafting in your own voice.
5 skills · hooks
Onboarding for people new to coding or to AI-assisted coding: setting up the machine, choosing what to build a first project with, and putting it online.
2 skills
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
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
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
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
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.