joeldevz
UserStop AI coding agents from losing context and shipping random code. Orchestrator + specialized sub-agents + structured plan. Claude Code, OpenCode.
Categories
Indexed Skills (7)
grill-me
Use when the user requests a non-trivial feature, change, or design decision before writing a PRD or plan. Do NOT use for trivial bug fixes, typos, or tasks crystal-clear from context.
prd
Use when the user requests a PRD, requirements document, feature spec, or product structure. Run AFTER grill-me has resolved the design tree.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
security
Use when the orchestrator reaches the security validation phase, or the user requests a security review (English or Spanish).
tdd-discipline
Use when the user opts into TDD or the task requires writing/modifying tests. Tests derive from the plan's Given/When/Then requirements. Optional for trivial bugfixes/docs.
triage
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.