Free · open source · no server, no database
Every dev tool, agent skill and app, in one free store
A free, open store of developer tools, AI agent skills and Flisk apps. Search any of them, and sign in with GitHub to add your own. No server, no database.
400 results
Find out what you really want before building: ask, compare approaches, write and approve a design doc.
Read the session transcripts to show why an agent session went wrong, with file and line proof.
Give each independent problem to its own sub-agent and run them side by side.
Carry out a written plan yourself, task by task, with test proof and a ledger, then one final review.
When work is done and green, pick merge, PR or discard, then clean up the branch and worktree.
Handle review comments with checks, not blind yes: understand, verify, then fix or push back.
Hand your finished work to a fresh reviewer sub-agent with the right context before it merges.
Run a plan with a fresh sub-agent per task, a review after each, and a broad review at the end.
Find the root cause before any fix, in four phases: investigate, compare, hypothesise, then fix.
Write the failing test first, watch it fail, write the least code to pass, then clean up.
Work in an isolated git worktree so your current branch stays untouched.
Session starter: check for a fitting skill and use it before answering or acting.
No saying done until you ran the check and read the output: tests, lint, build.
Turn a spec into a step-by-step plan with exact files, tests and commands for a new engineer.
Make or edit a skill like TDD: test the agent without it first, write it, then close loopholes.
Router: tells you which skill or flow to use, from idea to ship, for your situation.
Review changes since a commit two ways at once: coding standards and does it match the spec.
Shared words and rules for deep modules: small interface, lots of behaviour, clean seams.
Debug hard bugs and slowdowns by building a tight pass/fail feedback loop first.
Build and sharpen the project's domain language: write GLOSSARY.md and decision records (ADRs).
Add a Claude Code hook that blocks git push, reset --hard, clean -f, branch -D and similar.
Get interviewed hard about your plan or design until everything is clear.
Get grilled on your plan, while the agent writes the glossary and ADRs as you go.
Question the user round by round down a decision tree, with a suggested answer for each question.
Page 1 of 17Next →