tl;dv
tl;dvMeeting recorder with searchable transcripts and summaries.
Turn a retro board into two actions with owners.
Teams whose retros produce themes but no changes
Blameless incident analysis — different purpose, different care
Reads a retro board and produces a short note: themes with counts, what changed since last retro, and exactly two actions with owners and dates. The two-action limit is the design: a retro with ten actions changes nothing, which is why the same complaints return.
Clone the repository, then copy the skill folder into your agent's skills directory — ~/.claude/skills/ for Claude Code. Skills are plain files: no build step, no daemon.
npx skills add sprint-retroRead the SKILL.md before you install. A good skill states when it applies, what it must not do, and how to verify the result. A skill that only lists adjectives will change the agent's tone without improving its output — skip those.
Meeting recorder with searchable transcripts and summaries.
Notes that organise themselves around what you are working on.
Structured notes with a graph you actually design.
Searches and reads Drive files through a scoped OAuth grant: names, types, and extracted text for documents. It is the retrieval layer for a company's documents, whi…
Reads and writes spreadsheet ranges through a sheet-scoped grant: list sheets, read a range, append rows, update cells. It is the fastest way to give an agent a huma…
Searches and reads files in a Dropbox account, with optional upload and share-link creation. The useful pattern is lookup: the agent finds the deck or the contract a…