mistakenot-skills

End-to-end AI-agent task delivery: requirements, solution, plan, review, execute, and ship features through a structured plan-to-merge workflow.

20 skills

Reflection loop: mine learnings into a diary, and observe→refine→search reusable task rules.

4 skills

Build, run, validate, and manage A/B evals for skills in this repo: replay real tasks, compare skill versions on cost and quality, and validate the eval before trusting it.

2 skills

Structured ideation: generate high-impact feature ideas and run synthetic user-research simulations to decide what to build next.

2 skills

Design end-to-end assurance and testing strategies for autonomous agent-built software.

1 skill

Consult a council of independent coding-agent models (claude, codex, gemini, opencode, grok) for diverse, unled opinions on a question; strategies, members and prompt framings compose like an SDK.

1 skill

Customer discovery: mine real customer conversations for demand signals, jobs-to-be-done, and unmet needs.

1 skill

Build and maintain a project's ubiquitous language: a DDD glossary of canonical domain terms, kept in sync with the code.

1 skill

De-risk ideas before building: run exploratory tech spikes that validate assumptions and stress-test approaches.

1 skill

Relentlessly interrogate a plan, design, or decision to surface assumptions and edge cases, recording the outcomes as numbered ADRs.

1 skill

Machine-local handoff stack: push and pull short text notes between agent sessions using a JSONL store.

1 skill

Documentation maintenance: keep READMEs and docs in sync with the current state of the code.

1 skill

External-research skills: track open-source repos and mine their updates into a ranked backlog of ideas to borrow.

1 skill

Author rich single-file HTML docs — designs, plans, proposals, reports — with tabs, mermaid diagrams, code, file trees, and inline comment threads.

1 skill