sdd
claudeDocument definitions, interview skills and consistency checks for a solo project, from idea to tasks. Human in the loop; implementation is out of scope.
8 skills
Recommends an appropriate Claude or GPT model and effort level for an upcoming task.
Plugin model-picker from marketplace dev-toolkits in TerminalVelociraptor/claude-dev-marketplace. Commands read from the repo's manifest — today.
model-pickerRecommend which Claude/GPT model and effort level to use for an upcoming task. Use when the user is mid-conversation and asks something like "what model should I use for this", "should I switch models", "recommend a model/effort for X", or wants a model switch decision before starting a task.
pickerEvidence-grounded model and effort lookup for the model-picker skill. Launched by /model-picker:model-picker with the user's task, a constraint summary, and absolute paths to the bundled reference files. Returns a short recommendation; does not run the task or change models.
Document definitions, interview skills and consistency checks for a solo project, from idea to tasks. Human in the loop; implementation is out of scope.
8 skills
Turns Claude Code into an interactive coding teacher for deliberate practice. Two session modes over a shared teaching core, with a global spaced-repetition log.
5 skills · hooks
My personal workflow preferences for working with Claude Code.
3 skills
Tools to create a roadmap from a Claude plan with multiple work units, resume the work on fresh agents, and track execution.
1 skill
Cost and session telemetry as a Claude Code mod: an always-on status band (model, effort, git, context, cost, rate limits, cache), a per-turn cost row split by main thread, subagents and untracked spend, and a /telemetry details pane.
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.