Agent Skills by Ariff
Showing 16 vetted skills indexed across 1 GitHub repositories.
memory-sync
Synchronize task outputs to mem0-memory-mcp and obsidian-memory stores.
when-stuck
Identify stuck types and apply corresponding techniques from a dispatch table.
systematic-debugging
Reproduce, isolate, trace, fix, and verify software bugs systematically.
using-superpowers
Enforce mandatory skill usage and checklist-driven execution before task execution.
executing-plans
Execute implementation plans in batches with verification gates and status tracking.
root-cause-tracing
Trace bugs backward from symptoms to identify root causes.
hooks-reference
Implement and validate event-driven Claude Code hooks with hooks.json structure.
github
Generate human-style Git commit messages for code changes.
plugin-creator
Scaffold Claude Code plugin directories with manifests and templates.
brainstorming
Transform rough ideas into structured designs through phased questioning.
writing-plans
Create detailed implementation plans with granular tasks and exact file paths.
canvas-api
Connect to the Canvas LMS API for course data access.
verification-before-completion
Enforce a five-step verification gate before claiming task completion.
plugin-checker
Validate Claude plugin structure, manifests, and security hygiene.
subagent-driven-development
Deploy subagents for focused subtasks with explicit scope and success criteria.
defense-in-depth
Run four-layer validation pipelines across linting, tests, and end-to-end checks.