reflectlisted

Mine the session you are in for learnings that outlive it, and propose each one as a concrete change. It resolves this session's own transcript by a marker the run planted, normalizes it into a bounded record stream, sends three read-only lenses over it (judgment, tooling, divergent), synthesizes one Accepted / Rejected / Backlog list with the evidence behind every item, writes a plan file into a printed run cache, and waits: nothing outside that cache changes before you answer. Invoke ONLY on explicit reflection intent — the user says "reflect on this session", "capture what we learned", "what should we take from this session", or runs "/reflect". A run edits skill files and files public issues, so never infer that intent from a session ending, from a retrospective remark, or from a run that hit friction.
bostonaholic/team · ★ 11 · AI & Automation · score 78

Install: claude install-skill bostonaholic/team

# reflect — turn a finished session into durable learnings > Follow `skills/progress-tracking/SKILL.md`: this procedure has more than two steps — > seed one todo item per step below before starting and mark each complete as you go. A long session teaches things that die with it: the guidance that was missing, the command that cost four retries, the thing you did that no skill describes. `/reflect` reads the transcript of the session it was invoked from and proposes each durable learning as a change someone can accept or reject. Three things make it more than "summarize this session": - **It reads the session, not its own memory.** Compaction has already discarded the early turns from context, and those turns are where the corrections live. So the run resolves the session's transcript on disk and works from that file. - **Three lenses, then one list.** The lenses look for different things and report what they find. Sorting the findings — accepted, rejected, or handed to the tracker — happens once, afterwards, so one finding cannot be classified three ways. - **Nothing mutates before you answer.** The read-and-plan phase writes only inside its own run cache and prints where. Every change to a file you own, and every issue on a tracker, waits on an explicit approval. Model invocation is disabled (`disable-model-invocation: true`). A run rewrites `SKILL.md` files that every future run reads and creates issues that are public and irreversible, and no verificati