Przejdź do treści
Biblioteka skilli
Produktywność osobista · Analiza

recall

/recall

Odtwarza ostatni kontekst pracy z historii czatu, stanu i wspólnych zgłoszeń, a potem podaje krótki opis bieżącego stanu.

Repozytorium
shinstack ↗
Licencja
MIT
Ostatnia zmiana repozytorium
13.11.2026

Ocena i bezpieczeństwo

90/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść25 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
1
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 13.11.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Odtwarza ostatni kontekst pracy z historii czatu, stanu i wspólnych zgłoszeń, a potem podaje krótki opis bieżącego stanu.

Wyzwalacze z opisu

recall my work on Xcatch me upwhat have I been working onwhere did I leave off
Oryginalny opis (EN)

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.

Jak działa

  1. Output contract
  2. Resuming one specific prior chat or run (session pickup)
Sekcje z nagłówków SKILL.md, w oryginale · 44 linii, 1 068 słów
Podgląd SKILL.md
---
name: recall
description: "Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work."
---

# Recall

**Before you start or resume work, you rebuild the user's recent working context and hand back a tight capsule of where things stand now and what to do next.**

Keep it tight and on-topic. Read only what the in-scope threads need, then stop.

Your context lives in two records. Your own chat history holds what you did and decided. The shared record holds everything that happened around the same code under other names: the symptoms users keep reporting, the fixes that shipped and got reverted, the errors still firing in prod. That second record is what the `/shinstack:why` searches, across source control, the issue tracker, chat and issue channels, long-form docs, and error tracking. A feature with a long bug tail keeps most of its story there, so don't reconstruct it from your transcripts alone.

Transcripts live where your harness keeps them. Each file is JSONL. Find the active workspace's directory for your harness. If you can't tell which harness you are, check which of these exist for this workspace:

- **Claude Code:** `~/.claude/projects/<slug>/<session-id>.jsonl`. `<slug>` is the workspace path with every character that isn't a letter or digit turned into "-" (`/Users/you/proj` becomes `-Users-you-proj`).
- **Pi:** `~/.pi/agent/sessions/--<slug>--/<timestamp>_<id>.jsonl`. `<slug>` is the workspace path with the leading slash dropped and each "/" turned into "-" (`--Users-you-proj--`).
- **Codex:** `~/.codex/sessions/YYYY/MM/DD/rollout-*.jsonl`, not grouped by workspace. Keep only files whose first line has `payload.cwd` equal to the workspace path.
- **OpenCode:** `~/.local/share/opencode/storage/`. Sessions are JSON files under `session/<project-id>/`, with their messages under `message/` and `part/`.

1. Classify, then route. One specific prior chat to resume is just a direct read of that chat, not this. Turning habits into a durable skill is `automate-me`. A human-readable summary of your work is a different task. Recall loads working context across recent chats before you act. If the user already gave you a full state capsule (paths, branch, the change), use it and skip the mining.
2. Lock the scope before searching. Pin the window ("recent" is a real range, default the last 7 days), the topic if named, and the workspace (default the active one. Never read another project's transcripts without being asked). State the scope back. Never quietly turn "all" into "recent N".
3. Search this repo's chat history only. Order candidates by real modification time (`ls -t`), never by UUID name. Grep the topic first, then read only the matching chats and only their relevant regions, skipping the current chat and obvious noise (subagent, eval and test chats). For each chat note: topic, the user's goal, decisions, open threads, struggles and corrections, and artifacts (PRs, tickets, branches), citing the chat UUID. If more than about ten chats match, spawn up to three read-only `Agent` subagents (explorers, light weight), one per slice, each returning that same schema; otherwise do it yourself. The raw transcripts stay out of the main thread.
4. Sweep the shared record whenever the topic names a feature, file, subsystem, area, or bug. This is the default, not a judgment call, and "my work on X" does not exempt it. Hand it to the `/shinstack:why`'s source investigators (explorers, light weight), but steer their question from "why was this built this way" to "what's the current state, what's been tried and didn't hold, and what are users still reporting". Reuse its per-source playbooks, run the investigators in parallel with the chat-history mining, and inherit its posture: one investigator per source, null results are findings, skip an unavailable MCP and say so. Fold what comes back into the brief. Skip this step only for pure activity recall with no named target ("what did I do this week"), where your own history and live state are the entire answer.
5. Verify against live state. Take the PRs, branches, and tickets that the mining and the sweep surfaced and check them with `git` and `gh`. When the answer hinges on what an agent actually did (the tools it ran, files it read, errors it hit), read the full transcript, not just a trimmed local copy.
6. Write the brief to the contract below. Group by thread. Stay on the named topic.

## Output contract

Lead with the capsule, then the thread status, then the problems, then the next move. Deeper detail goes below or gets cut.

- **Capsule.** At most 5 bullets. What this work is and where it stands overall.
- **Threads.** One line each, prefixed with exactly one status tag: `[merged #N]`, `[open PR #N]`, `[in flight <branch>]`, `[verified, uncommitted]`, `[reverted #N]`, or `[planned, not started]`. A thread with no tag is not done yet, so tag it.
- **Problems.** At most 5, the recurring ones. Include the symptoms users keep reporting and any fix that shipped and was reverted, so the next attempt starts where the last one failed.
- **Next move.** The single most useful next action, concrete.

An adjacent feature or ticket stays out unless it blocks this one. When the capsule and thread lines outgrow a screen, cut detail before you cut threads. Write the brief through the `/shinstack:unslop`, cite chat findings by UUID and shared-record findings by their source (PR #, ticket ID, chat permalink, error-tracker issue), and sanitize private context before any public output.

**Reply:** the brief, to the contract above.

## Resuming one specific prior chat or run (session pickup)
When the user points at one prior trail (a transcript, a branch, a run log, a resume note), read it instead of mining everything.
1. Locate the trail in this workspace only: the chat transcript, the pushed branch, `decisions.tsv` or a `.audit/*-resume.md` note. Read the overview and the last messages first, then scan back for decision points. Parse a long transcript in a subagent and keep the reduced timeline in the main thread.
2. Reconstruct state: the branch and worktree, what landed (`git log`, `git diff` against the base), open todos, decisions made. The prior trail is authoritative input. Resist re-deriving it.
3. Diff done against pending. Name the resume point. Do not re-run the prior repro or redo completed work: "let me verify from scratch" means you are treating the trail as untrustworthy.
4. Route the remaining work to the matching playbook: continue the execution, ship a finished recommendation, ratify or override a prior conclusion, or write up a failed run.
5. Verify the inherited claims against the original goal on the real artifact (prove-it-works). A passing prior self-report is not the proof.

Wersje

RepozytoriumWynikLicencja
Ta strona · guangshinhaha/shinstack90MIT
gtapps/hermitd100MIT
wenlan-app/wenlan100Apache-2.0
wenlan-app/wenlan100Apache-2.0
davepoon/buildwithclaude100MIT
rohitg00/agentmemory100Apache-2.0
smart-ai-memory/attune-ai100Apache-2.0
spencerneutron/Synapse100MIT
cihanatak/lr-memory100MIT

Migawka bazy z 13.11.2026 · wersja paczki 48ee646076c0 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100spirit-world
    Odzyskuje kontekst ostatniej pracy z historii czatów Claude Code i Codexa, stanu gita i PR-ów oraz wspólnego zapisu przed wznowieniem.
  • 90thinkweave-recall
    Przywołuje wcześniejsze decyzje i kontekst z ThinkWeave tylko do odczytu, na wyraźne polecenie użytkownika.
  • 100obsidian-brief
    Syntetyzuje brief kontekstowy z ostatnich logów sesji i zapisów w Obsidianie dla bieżącego projektu na początku pracy, w trybie odczytu.
  • 100m0-recall
    Przypomina kontekst pracy: czyta ostatni wątek operacyjny M0 dla każdego projektu od najnowszego z demona M0, gdy pada pytanie, gdzie skończyliśmy lub co dalej.
  • 85session-continuity
    Wznawia wcześniejszą sesję, odtwarza ostatni kontekst projektu, zatrzymuje pracę na prośbę i przekazuje ją nowemu agentowi.
  • 98state
    Aktualizuje zapis stanu projektu i odtwarza bieżący kontekst na początku sesji.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.