agentleFS
duthahoduthaho/skillhub/.claude/skills/revisit/SKILL.md

revisit

Skill9 starsChanged 16 days agoMITView on GitHub

Revisit dashboard — one scan of everything you parked to re-check later, across every skill's memory. Reads out/*/tracker.md and the other memory files skills leave behind (ideate PARK "revive when", verdict/scout revisit-when triggers, refactor WATCH candidates, learn spaced-repetition due dates, jobfit roles to re-check) and surfaces what's due now: date-based items past their date, trigger-based items whose condition may have fired. Renders one prioritized "due to re-check" list in chat — grouped by skill, most overdue first — quoting the exact tracker line and its revive trigger so you can act or defer. Strictly read-only: it never edits a tracker or fires the follow-up skill; it points, you decide. Use for "what do I need to revisit", "what's due to re-check", "anything parked worth reviving", "show my revisit queue" — e.g. "/revisit", "/revisit ideate".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. mik2win/foureyes★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository21 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read each memory file and pull every line carrying a revisit signal.

    line 48
  2. Distinctive:

    Don't fire or resolve anything — classification only.

    line 79
  3. Distinctive:

    Completion criterion: every item is DUE or NOT YET, each with a one-line reason.

    line 81
  4. Distinctive:

    Never auto-run a follow-up.

    line 96

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

revisit — what you parked, now due

/revisit — scan every skill's memory for items due to re-check /revisit <skill> — only that skill's tracker (e.g. /revisit ideate)

Skills that judge under uncertainty don't just decide — they record a trigger for revisiting the decision: ideate PARKs an idea "revive when X", verdict stamps "revisit-when", scout/refactor leave WATCH items, learn schedules the next review by date. Scattered across out/*/, those triggers rot unseen. This skill is the one place that gathers them and asks a single question: what is due to re-check right now?

It is strictly read-only — the same contract as daybrief. It never edits a tracker, never marks anything revived, never runs the follow-up skill. It surfaces; you decide.

Step 0 — Locate the memory

Today's date is date +%F (compute it; don't hardcode). Then find out/ in the current project.

  • No out/, or no memory files under it → say so plainly and stop. Nothing to revisit is a valid, complete answer (keyless, graceful — never invent items).
  • /revisit <skill> → restrict the scan to out/<skill>/ only.

Completion criterion: the set of memory files to scan is fixed, or a clean "nothing to revisit yet" is reported.

Step 1 — Collect the revisit signals

Read each memory file and pull every line carrying a revisit signal. Known shapes (don't limit to these — any "revive/revisit/recheck/due" marker counts):

SourceSignal to pull
out/ideate/tracker.mdPARK rows with a "Revive when …" reason
out/verdict/*.mdrevisit-when triggers on a past verdict
out/scout/tracker.mdWATCH items and their revive condition
out/refactor/tracker.mdWATCH candidates deferred to a trigger
out/learn/*.mdnext-review due dates (spaced repetition)
out/jobfit/tracker.mdroles marked to re-check later

Skip anything already resolved (SHIPPED, DONE, DROP, applied) — a DROP is not a revisit. Capture for each item: source skill, the verbatim line, and its trigger (a date, or a condition in prose).

Completion criterion: a flat list of open revisit items, each tagged with source skill and its trigger.

Step 2 — Classify each item

Sort every item into exactly one bucket:

  • DUE — a date-based trigger whose date is on or before today, or a condition-based trigger that plausibly has fired given what you can see in the repo/trackers (state the evidence). When unsure whether a condition fired, mark DUE and say why it's worth a look — a false "check this" is cheaper than a missed revive.
  • NOT YET — date still in the future, or condition clearly not met. Keep it, but below the fold, with the unmet trigger shown.

Don't fire or resolve anything — classification only.

Completion criterion: every item is DUE or NOT YET, each with a one-line reason.

Step 3 — Render the queue

One prioritized list in chat:

  • DUE first, most overdue at the top (oldest date, or longest-standing condition). Group by source skill. For each: the quoted line, its trigger, why it's due, and the next skill to run if the user chooses to act (e.g. "→ /ideate to re-diverge", "→ /verdict revisit <brief>").
  • NOT YET collapsed underneath as a short "watching" list — item + the trigger not yet met — so the user sees the horizon without noise.
  • Nothing DUE → say so in one line; the watching list is still worth showing.

Never auto-run a follow-up. Naming the next skill is a suggestion the user acts on — the read-only contract holds to the last line.

Completion criterion: a single grouped, prioritized queue in chat; every DUE item names the skill that would act on it; nothing was written or triggered.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.