writing

The day, run for you. A morning brief that ranks today against what changed and caps itself at seven items, a catch-up for when you were away that leads with what still needs you, the questions nobody ever answered, your mail and chat sorted by what needs you without touching anything, and a handover draft for before you go away. Needs the files setup writes and at least one configured source; every run names what it read, what it could not check, and the dates it covered. Nothing here sends anything, and nothing writes except the plugin's own snapshot, suppression and handover-pool files in your project folder.

5 skills

The one that judges how you worked, not what you produced. Compares your week against the priorities you confirmed, ranks what is in front of you against them, keeps a running record of what actually went well in your own words, and gives feedback against a standard you set. Needs the files setup writes, and time-spent needs a configured calendar; source-based runs open by naming the evidence and the dates they actually read. Nothing here writes except the wins record, and only with your yes.

4 skills

Three skills that compare you and your asks against the outside world: a cited brief on any topic, kept as a Word document and rerun on request; what strong looks like in your role right now against what you said you are working on; and the better shape for the thing you are about to ask for. The cited products need live web access and stop without it. Its triggers are lines in the project instructions, so a project set up before learning was installed has none until a skill hands over the paste.

3 skills

Runs once. Gets you from "I installed this" to "it knows who I am, and something runs tomorrow morning without me." Finds what it can, asks only what it cannot, shows you the whole suggestion, and writes the files every other skill reads. Its check skill tells you at any time which skills can run and which are blocked by which file.

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