Skip to main content

hgbeigi/claude-tools

Latest recorded source activity
SkillsMP catalog refreshed
skills collected
9
GitHub stars
0
GitHub forks
0

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Loading the repository README…

BEIIG
BEIIG
@hgbeigi
Skill release postMaintain Skills
Post summary

Opens household Claude skills that audit subscriptions from local CSVs, vet outside skills before install, and file corrections into the owning skill file.

Skills in this repository

classification pending

Showing 9 of 9 collected skills.

occupation
unclassified
description

Search the user's own notes and files before stating a fact about their health, money, home, car, insurance or accounts, and before asking them a question. Use when the user says "you should have known", "we already have that", "you have that already", "why…

updated
occupation
unclassified
description

Turns a correction from the user into a dated rule in the skill, agent or instruction file that caused the mistake, in the same session, and says where it went. Use when the user says "that's wrong", "not what I asked", "I told you before", "why didn't you",…

updated
occupation
unclassified
description

How to brief a helper agent, and how many to send at once. Use when the user says "send an agent", "send agents", "fan out", "split this up", "get a helper on it", "do these in parallel", or before you start any helper agent with a prompt you wrote yourself.

updated
occupation
unclassified
description

The handback shape for work given to a helper agent, and the read-back before anything is called done. Use when a helper finishes, or when the user asks "is it done?", "did you check?", "did you verify?", "did you finish?".

updated
occupation
unclassified
description

The register of what the tools cannot do, and the route that works instead. Read it before saying "impossible", "can't access", "blocked", "not supported" or "it won't open". Use when the user says "is there any way", "can we connect", "did you try the…

updated
occupation
unclassified
description

A read-only second check of a plan, document or finished piece of work before it is called done. Use when the user says "review this", "check your work", "is it ready?", "grade it", "pre-mortem", "independent check", or before you write "ready" or "done" on…

updated
occupation
unclassified
description

Ends a session so the next one can pick up without the old conversation. Use when the user says "close the session", "wrap up", "we're done", "handoff", "hand off", "write a prompt for a new session", "save where we are", or "commit and push".

updated
occupation
unclassified
description

Lists every recurring charge in a folder of bank and card CSV exports, with cadence, last amount, the paying account and a "still used" column you fill in. Use when the user says "what subscriptions do I have", "what am I paying every month", "cancel…

updated
occupation
unclassified
description

Checks an outside skill, plugin, MCP server, script or repository before it is installed or run, and ends in a written adopt, rebuild or reject verdict. Use when the user says "install this skill", "try this plugin", "add this MCP", "I found this repo", "is…

updated
Showing 9 of 9 collected skills.