GitHub

drift-analysis

Knowledge and patterns for analyzing project state, detecting plan drift, and creating prioritized reconstruction plans....

by agent-sh

github

enhance-agent-prompts

Analyze agent prompt files for prompt engineering best practices. const args = '$ARGUMENTS'.split(' ').filter(Boolean); ...

by agent-sh

github

discover-tasks

Discover tasks from configured sources, validate them, and present for user selection. Invoked during Phase 2 of /next-t...

by agent-sh

github

deslop

Clean AI slop from code with certainty-based findings and auto-fixes. const args = '$ARGUMENTS'.split(' ').filter(Boolea...

by agent-sh

github

consult

Cross-tool AI consultation: query another AI CLI tool and return the response. Invoke this skill when: User wants a seco...

by agent-sh

github

enhance-cross-file

Analyze cross-file semantic consistency across agents, skills, and workflows. const args = '$ARGUMENTS'.split(' ').filte...

by agent-sh

github

enhance-prompts

Analyze prompts for clarity, structure, examples, and output reliability. const args = '$ARGUMENTS'.split(' ').filter(Bo...

by agent-sh

github

maintain-cross-platform

Purpose: Comprehensive knowledge of AgentSys's cross-platform infrastructure for release preparation, validation, and ma...

by agent-sh

github

orchestrate-review

Multi-pass code review with parallel Task agents, finding aggregation, and iteration until clean. Select conditional spe...

by agent-sh

github

web-auth

Authenticate to websites by opening a headed browser for the user to complete login manually. The agent monitors for suc...

by agent-sh

github

perf-profiler

Run profiling tools and capture hotspots with evidence. Follow docs/perf-requirements.md as the canonical contract. cons...

by agent-sh

github

debate

Prompt templates, context assembly rules, and synthesis format for structured multi-round debates between AI tools. Pars...

by agent-sh

github

validate-delivery

Autonomously validate that a task is complete and ready to ship. function checkReviewStatus(reviewResults) { if (!review...

by agent-sh

github

web-browse

Headless browser control for navigating and interacting with web pages. All actions run through a single CLI invocation....

by agent-sh

github

pdf

This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced featur...

by ageerle

github

docx

A .docx file is a ZIP archive containing XML files. | Task | Approach | |------|----------| | Read/analyze content | pan...

by ageerle

github

xlsx

Every Excel model MUST be delivered with ZERO formula errors (#REF!, #DIV/0!, #VALUE!, #N/A, #NAME?) Study and EXACTLY m...

by ageerle

github

videodb

Perception + memory + actions for video, live streams, and desktop sessions. Start/stop a desktop session capturing scre...

by affaan-m

github

token-budget-advisor

Intercept the response flow to offer the user a choice about response depth before Claude answers. User wants to control...

by affaan-m

github

skill-stocktake

Slash command (/skill-stocktake) that audits all Claude skills and commands using a quality checklist + AI holistic judg...

by affaan-m

github

springboot-verification

Run before PRs, after major changes, and pre-deploy. Before opening a pull request for a Spring Boot service After major...

by affaan-m

github

research-ops

Use this when the user asks to research something current, compare options, enrich people or companies, or turn repeated...

by affaan-m

github

perl-testing

Comprehensive testing strategies for Perl applications using Test2::V0, Test::More, prove, and TDD methodology. Writing ...

by affaan-m

github

lead-intelligence

Agent-powered lead intelligence pipeline that finds, scores, and reaches high-value contacts through social graph analys...

by affaan-m

github