Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
init-override
Create a symlink from AGENTS.md to CLAUDE.md in the current project directory. Use when the user wants to initialise a project to use AGENTS.md as the memory file instead of CLAUDE.md.
sofer/.agents 4
-
commit
Git workflow operations with Conventional Commits. Supports subcommands - branch (create feature branch), commit (stage and commit changes), pr (create pull request), merge (merge PR). Automatically available when the current directory is a git repository. Use when user needs git operations during development workflow.
sofer/.agents 4
-
contact-research
Research a person given their name and email, returning a brief profile with role, company, LinkedIn summary, and previous interactions
sofer/.agents 4
-
design
Plan architecture and components for a single user story. Use after spec phase to create a technical design before implementation. Produces design documents that guide stubs and implementation.
sofer/.agents 4
-
feature
Implement a feature using TDD. Works standalone (user describes what to build) or as part of the orchestrated pipeline (story and context provided). Handles complexity scaling, design, stubs, tests, implementation, migrations, refactoring, and review. Use when building a feature in an existing codebase.
sofer/.agents 4
-
implement
Write code to pass all tests (TDD green phase). Expect 100% test pass rate. Use after tests are written to implement the actual functionality.
sofer/.agents 4
-
email-voice-draft
Draft an email reply in the user's voice using their business context and Notion knowledge
sofer/.agents 4
-
anonymise
Anonymise CSV files by removing personal identifying information and adding datetime stamps. Use when user wants to process a new CSV file or strip PII from data.
sofer/.agents 4
-
skill-installer
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
sofer/.agents 4
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
sofer/.agents 4
-
deploy
Ship code to target environment. Use after code is merged to deploy to staging or production. Handles build, artifact creation, and deployment orchestration.
sofer/.agents 4
-
code-review
Review code for quality, security, and standards compliance. Works as a pipeline gate after refactor phase, or standalone against PR URLs, branch names, commit ranges, or file lists.
sofer/.agents 4
-
cortex
CLI for managing the Cortex email automation pipeline. Use this skill when the user wants to query emails, check queue status, trigger backfills, view classifications, or manage the email triage system. Triggers on keywords like "cortex", "email pipeline", "queue status", "classification", "backfill", "triage".
devonjones/cortex-utils
-
claim-extraction
Extract structured claims, predictions, hints, and opinions from AI research content. Use when processing tweets, blog posts, substacks, or other content from AI researchers to identify substantive assertions about AI capabilities, limitations, and progress.
rickoslyder/HypeDelta
-
digest-generation
Generate a weekly AI intelligence digest from synthesized topic analyses and hype assessments. Use after synthesis and hype assessment to produce a readable, opinionated summary for sophisticated technical readers.
rickoslyder/HypeDelta
-
prediction-tracking
Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.
rickoslyder/HypeDelta
-
topic-synthesis
Synthesize claims across multiple sources to identify consensus, disagreements, and emerging narratives on AI research topics. Use when you have claims from both lab researchers and critics on the same topic and need to understand where they agree, disagree, and what the overall hype level is.
rickoslyder/HypeDelta
-
content-filter
Filter and classify AI research content for relevance, topic, and author category. Use for bulk triage of raw content before detailed claim extraction.
rickoslyder/HypeDelta
-
hint-detection
Detect hints about unreleased AI research or capabilities from lab researcher communications. Use when analyzing tweets, posts, or interviews from people at major AI labs to identify signals about upcoming work.
rickoslyder/HypeDelta
-
hype-assessment
Assess overall hype levels across AI topics by comparing lab researcher enthusiasm against critic skepticism. Use after topic synthesis to identify which topics are overhyped, underhyped, or accurately assessed by the field.
rickoslyder/HypeDelta
-
gmacko-dev-issue-create
Use when (1) creating GitHub issues from feature plans or bug reports, (2) documenting bugs found during development, (3) managing the project backlog. Creates well-structured GitHub issues with templates and labels.
gmackie/vercel-expo-app-template 1
-
gmacko-dev-pr-review
Use when (1) reviewing a pull request against coding standards, (2) verifying PR meets acceptance criteria from feature plan, (3) checking for common issues before merge. Reviews PRs against plan and project standards.
gmackie/vercel-expo-app-template 1
-
gmacko-release-prepare
Use when (1) preparing a release for staging or production, (2) generating release notes and changelog, (3) verifying environment readiness before deployment. Prepares all artifacts needed for a release.
gmackie/vercel-expo-app-template 1
-
gmacko-release-deploy-web
Use when (1) deploying web application to Vercel staging or production, (2) monitoring deployment progress, (3) running post-deployment verification. Manages Vercel deployment workflow with safety checks.
gmackie/vercel-expo-app-template 1