custom-reviewer
claudecodexMulti-perspective code & plan reviews orchestrated by a shared reviewer agent.
4 skills · 2 agents
GitHub PR lifecycle skills — open, rebase-merge, analyze reviews, and reply to review threads.
Plugin git-skills from marketplace ai-agent-plugins in kimharry99/ai-agent-plugins. Commands read from the repo's manifest — 1 month ago.
open-prOpen a GitHub pull request from the current branch. Analyzes ALL commits since the branch diverged from main (not just the latest), pushes if needed, then creates the PR. PR body is written in Korean by default. Use when the user says "open PR", "create PR", "push and open PR", "make a pull request"
pr-completeComplete a branch PR lifecycle end to end: open the PR, analyze reviews, apply only agreed review feedback, run one code-review gate, merge the PR, update main, and clean up any worktree and local branch. Use when the user says \"complete PR workflow\", \"open and merge PR\", \"PR 만들고 병합까지\", \"PR 끝
pr-mergeFull PR merge workflow — rebases the current branch onto its target (defaults to main), force-pushes, verifies unresolved review threads have replies and resolves them, verifies the Test Plan, re-checks for new unresolved threads, and merges via a merge commit. Use when the user says: (1) "merge PR"
pr-review-analyzeFetch and analyze all reviews on a GitHub pull request. Evaluates each comment's validity against the actual code at HEAD (Agree / Disagree / Unclear with reasoning) and consolidates feedback into Critical / Important / Suggestion categories with a per-reviewer summary. Use when the user says "analy
pr-review-applyApply review feedback to code, commit and push the changes, then reply to each review thread. Intended to run after /pr-review-analyze — by invocation time the user has already analyzed reviews, decided what to address, and applied the code changes. Use when the user says "apply review feedback", "a
Multi-perspective code & plan reviews orchestrated by a shared reviewer agent.
4 skills · 2 agents
Archive work records and search prior evidence in a user-configured Knowledge DB.
2 skills
Create picture-led HTML explanations for people new to a topic at age5, middle, or college presentation density. Use $eli5 with a topic and optional level.
1 skill
Convert implementation plans into grounded, structured goal prompt text.
1 skill
Python convention guidance for OOP, style, test layout, and test patterns.
1 skill
Read-only SLURM guidance and generic SBATCH script generation.
1 MCP server
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
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.