dominikwozniak/dw-solo-skills

dominikwozniak/dw-solo-skills

Skill Claude Code

Read-only environment diagnostic for a solo-lane repo: whether the tools the hooks and skills assume are installed, and whether the guardrails and the pre-commit really fire here or are silently skipping, each gap reported with a copy-paste fix.

dominikwozniak/dw-solo-skills

Skill Claude Code

Interview the user to sharpen a vague, half-formed or ambiguous idea into decided requirements before any of it gets built — a round asks every question whose prerequisites are settled, hardest first, each with a recommended answer, then plays back what is decided and what is still open, so the thinking is finished…

dominikwozniak/dw-solo-skills

Skill Claude Code

Compact the live session into .ai/work/ /HANDOFF.md — how far into the current task you are, what is applied but uncommitted, and which dead ends are already ruled out, so the next context window resumes mid-task. Explicit-invoke only.

dominikwozniak/dw-solo-skills

Skill Claude Code

Continue the change you are in the middle of, from where the last session had to leave it: catch up on where it stands and what is left, then build every unticked task, one commit each. Its state is read back from the doc, never from the conversation, so it survives a /clear.

dominikwozniak/dw-solo-skills

Skill Claude Code

Walk .ai/backlog/ and decide every entry out loud: drop what is stale or already done, do what is cheap and unblocked, bundle what ships with a cousin, leave the rest. Explicit-invoke only.

dominikwozniak/dw-solo-skills

Skill Claude Code

Cut the AI tells out of text a human will read — a PR body, a commit body, a release note — without flattening it into something voiceless. Refuses agent-facing artifacts by name. Explicit-invoke only.