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.
787 results
Red-green TDD with tests at agreed seams that check behaviour through public interfaces.
Turn the current chat into a spec and publish it to the issue tracker, no more interview.
Split a plan or spec into thin vertical tickets, each saying which tickets block it.
Move issues and outside PRs through triage states, check them, and write briefs agents can follow.
Plan a job too big for one session as a map of decision tickets, settled one by one.
Make a bash wizard that walks a human through manual steps: cloud setup, secrets, a cutover.
Style guide for docs agents read: skills, AGENTS.md and CLAUDE.md, with context pointers.
Catch repeat AI coding bugs with sandbox API tests and a bug-check flow.
Run post-deploy UI checks in a real browser: console errors, flows, screenshots.
Watch a live URL after release for errors, slow pages and broken endpoints.
Map an unfamiliar repo and write an onboarding guide plus a starter CLAUDE.md.
Baseline coding rules: clear names, immutability, KISS, DRY, YAGNI.
Review staged changes and write a Conventional Commits message.
Ship safe DB migrations: reversible, zero-downtime renames, safe indexes, backfills.
Deploy with rolling, blue-green or canary, Docker, health checks and rollback.
Block the first edit until the agent shows facts about importers and schemas.
Pick a branching flow, write clean commits, merge vs rebase, fix conflicts.
Design ports and adapters: domain core, use cases, testable boundaries.
Build MCP servers with the TypeScript SDK: tools, resources, Zod, transports.
Warn before rm -rf, force push, DROP TABLE; lock edits to one folder.
Research existing libraries and tools before writing custom code.
Security checklist for auth, user input, secrets, endpoints and payments.
Scan the .claude folder, hooks and MCP servers for bad config and injection.
TDD loop: failing test first, smallest fix to green, refactor, 80% coverage.
← PreviousPage 3 of 33Next →