luabagg/agent-skills

Collection of skills, tools and workflows

This repository also configures its own agents. See what agent-skills tells them →

3Stars on the repository
13Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

agentfolio-operator

01

luabagg/agent-skills

Skill Claude CodeCodex

Use when configuring this Agentfolio collection, selecting Pi/Cursor/OpenCode harness workflows, changing model policy, or choosing plan/apply commands.

not rated 3 changed 5d ago A 33 tokens original MIT

branch-port

02

luabagg/agent-skills

Skill Claude CodeCodex

Use when a feature must move between branches that have diverged too far for rebase or merge to be practical.

not rated 3 changed 1mo ago A 26 tokens original MIT

memory-palace

03

luabagg/agent-skills

Skill Claude CodeCodex

Use when the user asks to search, ingest, or audit their Obsidian knowledge vault.

not rated 3 changed 1mo ago A 23 tokens original MIT

luabagg/agent-skills

Skill Claude CodeCodex

Use when the user asks to translate, correct English, polish a message, adapt tone, or restructure text and wants clean copy-paste output. For removing AI-sounding patterns, use humanizer.

not rated 3 changed 1mo ago A 45 tokens original MIT

thorough-pr-review

05

luabagg/agent-skills

Skill Claude CodeCodex

Use when the user asks to review a pull request, evaluate diff-level merge-readiness, or audit the current branch before opening a PR. Triggers include "review this PR", "review my branch", "code review", or a GitHub PR URL paired with review intent. For pure security reviews, prefer security-review instead.

not rated 3 changed 1mo ago A 73 tokens original MIT

code-comments

06

luabagg/agent-skills

Skill Claude CodeCodex

Use when writing, editing, or reviewing a code comment: a function or type doc comment (JSDoc, docstring), a field or union member comment, a constant, an inline comment in a function body, a TODO, a file header, or a README sentence that states a measured fact.

not rated 3 changed today A 64 tokens original MIT

cognitive-refactor

07

luabagg/agent-skills

Skill Claude CodeCodex

Use when restructuring code so a reader can follow it: a complexity threshold fails, a function is long, nested, or full of else-if branches, a flag parameter or a constant parameter clutters a call, a function or task does two jobs, a result is a sentinel or a bag of answers, or files mix unrelated flows.

not rated 3 changed 5d ago A 72 tokens original MIT

luabagg/agent-skills

Skill Claude CodeCodex

Use when adding, reviewing, or deleting tests, deciding whether a function needs coverage, or when a suite enumerates branches, signs, empty values, or implementation steps without naming the behavior at risk.

not rated 3 changed 1mo ago A 45 tokens original MIT

code-naming

09

luabagg/agent-skills

Skill Claude CodeCodex

Use when naming or renaming TypeScript code: an export, a public API or barrel file, a type, an API request or response type, a function, a variable, a boolean flag, a result field, a constant, or a file. Also use when asked to propose better names, or when a proposed rename only adds a word to the old name.

not rated 3 changed today A 78 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: