Przejdź do treści
Biblioteka skilli
Programowanie · Automatyzacja

ck

/ck

Prowadzi pamięć projektu między sesjami Claude Code: zapisuje decyzje i kolejne kroki, a po starcie wczytuje krótki opis projektu.

Licencja
MIT
Ostatnia zmiana repozytorium
28.10.2026

Ocena i bezpieczeństwo

100/ 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.
Treść35 / 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
10
Skrypty
9
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 28.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

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

Co sprawdzić przed instalacją
  • 9 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.

Skrypty: commands/forget.mjs, commands/info.mjs, commands/init.mjs, commands/list.mjs, commands/migrate.mjs, commands/resume.mjs, commands/save.mjs, commands/shared.mjs, hooks/session-start.mjs

Co robi i kiedy

Prowadzi pamięć projektu między sesjami Claude Code: zapisuje decyzje i kolejne kroki, a po starcie wczytuje krótki opis projektu.

Oryginalny opis (EN)

Persistent per-project memory for Claude Code (Context Keeper) driven by deterministic Node.js /ck commands: init, save, resume, info, list, forget, and v1-to-v2 migrate, plus a SessionStart hook that injects a compact project brief. Use when context must survive across sessions, saving session state with next steps and decisions, resuming where a previous session left off, or picking up a project without re-explaining it.

Jak działa

  1. Data Layout
  2. Commands
  3. SessionStart Hook
  4. Rules
Sekcje z nagłówków SKILL.md, w oryginale · 158 linii, 705 słów
Podgląd SKILL.md
---
name: ck
description: "Persistent per-project memory for Claude Code (Context Keeper) driven by deterministic Node.js /ck commands: init, save, resume, info, list, forget, and v1-to-v2 migrate, plus a SessionStart hook that injects a compact project brief. Use when context must survive across sessions, saving session state with next steps and decisions, resuming where a previous session left off, or picking up a project without re-explaining it."
category: testing
allowed-tools: "Read, Grep, Glob, Bash, Edit, Write"
file_names: ["SKILL.md", "commands/forget.mjs", "commands/info.mjs", "commands/init.mjs", "commands/list.mjs", "commands/migrate.mjs", "commands/resume.mjs", "commands/save.mjs", "commands/shared.mjs", "hooks/session-start.mjs"]
metadata:
  origin: ECC
  architecture: GINA-Sovereign-Multi-Agent
  security_charter: GINA-SEC-7L-2026
  memory_topology: 3-tier-L1-L2-L3
  sandbox_policy: "--cap-drop=ALL"
  dlp_leakage_score: "0.00"
---


# ck — Context Keeper

You are the **Context Keeper** assistant. When the user invokes any `/ck:*` command,
run the corresponding Node.js script and present its stdout to the user verbatim.
Scripts live in the `commands/` directory next to this SKILL.md (for example
`${GINA_HOME:-~/.gina}/skills/ck/commands/` for a manual install, or the ck skill inside the ECC
plugin). The commands below refer to the skill directory as `${CLAUDE_SKILL_DIR}`,
which Claude Code fills in; in other hosts, replace it with the absolute path of the
directory containing this SKILL.md. Run the scripts from the project directory; do not
`cd` into the skill directory, because the scripts use the current directory as the
project path.

---

## Data Layout

```
${GINA_HOME:-~/.gina}/ck/
├── projects.json              ← path → {name, contextDir, lastUpdated}
└── contexts/<name>/
    ├── context.json           ← SOURCE OF TRUTH (structured JSON, v2)
    └── CONTEXT.md             ← generated view — do not hand-edit
```

---

## Commands

### `/ck:init` — Register a Project
```bash
node "${CLAUDE_SKILL_DIR}/commands/init.mjs"
```
The script outputs JSON with auto-detected info. Present it as a confirmation draft:
```
Here's what I found — confirm or edit anything:
Project:     <name>
Description: <description>
Stack:       <stack>
Goal:        <goal>
Do-nots:     <constraints or "None">
Repo:        <repo or "none">
```
Wait for user approval. Apply any edits. Then pass the confirmed JSON to save.mjs --init
through a quoted heredoc (never `echo '...'`: an apostrophe in any field would end the
quoted string and hand the rest to the shell):
```bash
node "${CLAUDE_SKILL_DIR}/commands/save.mjs" --init <<'CK_JSON'
<confirmed-json>
CK_JSON
```
Confirmed JSON schema: `{"name":"...","path":"...","description":"...","stack":["..."],"goal":"...","constraints":["..."],"repo":"..." }`

---

### `/ck:save` — Save Session State
**This is the only command requiring LLM analysis.** Analyze the current conversation:
- `summary`: one sentence, max 10 words, what was accomplished
- `leftOff`: what was actively being worked on (specific file/feature/bug)
- `nextSteps`: ordered array of concrete next steps
- `decisions`: array of `{what, why}` for decisions made this session
- `blockers`: array of current blockers (empty array if none)
- `goal`: updated goal string **only if it changed this session**, else omit

Show a draft summary to the user: `"Session: '<summary>' — save this? (yes / edit)"`
Wait for confirmation. Then pass the JSON to save.mjs through a quoted heredoc:
```bash
node "${CLAUDE_SKILL_DIR}/commands/save.mjs" <<'CK_JSON'
<json>
CK_JSON
```
JSON schema (exact): `{"summary":"...","leftOff":"...","nextSteps":["..."],"decisions":[{"what":"...","why":"..."}],"blockers":["..."]}`
Display the script's stdout confirmation verbatim.

---

### `/ck:resume [name|number]` — Full Briefing
```bash
node "${CLAUDE_SKILL_DIR}/commands/resume.mjs" [arg]
```
Display output verbatim. Then ask: "Continue from here? Or has anything changed?"
If user reports changes → run `/ck:save` immediately.

---

### `/ck:info [name|number]` — Quick Snapshot
```bash
node "${CLAUDE_SKILL_DIR}/commands/info.mjs" [arg]
```
Display output verbatim. No follow-up question.

---

### `/ck:list` — Portfolio View
```bash
node "${CLAUDE_SKILL_DIR}/commands/list.mjs"
```
Display output verbatim. If user replies with a number or name → run `/ck:resume`.

---

### `/ck:forget [name|number]` — Remove a Project
First resolve the project name (run `/ck:list` if needed).
Ask: `"This will permanently delete context for '<name>'. Are you sure? (yes/no)"`
If yes:
```bash
node "${CLAUDE_SKILL_DIR}/commands/forget.mjs" [name]
```
Display confirmation verbatim.

---

### `/ck:migrate` — Convert v1 Data to v2
```bash
node "${CLAUDE_SKILL_DIR}/commands/migrate.mjs"
```
For a dry run first:
```bash
node "${CLAUDE_SKILL_DIR}/commands/migrate.mjs" --dry-run
```
Display output verbatim. Migrates all v1 CONTEXT.md + meta.json files to v2 context.json.
Originals are backed up as `meta.json.v1-backup` — nothing is deleted.

---

## SessionStart Hook

The hook at `hooks/session-start.mjs` in this skill's directory must be registered in
`${GINA_HOME:-~/.gina}/settings.json` to auto-load project context on session start. For a manual
install in `${GINA_HOME:-~/.gina}/skills/ck`:

```json
{
  "hooks": {
    "SessionStart": [
      { "hooks": [{ "type": "command", "command": "node \"$HOME/.gina/skills/ck/hooks/session-start.mjs\"" }] }
    ]
  }
}
```

Use `$HOME`, not `~`: the shell does not expand `~` inside double quotes. If ck lives
elsewhere (for example inside the ECC plugin), use the absolute path of its
`hooks/session-start.mjs` instead.

The hook injects ~100 tokens per session (compact 5-line summary). It also detects
unsaved sessions, git activity since last save, and goal mismatches vs CLAUDE.md.

---

## Rules
- Always expand `~` as `$HOME` in Bash calls.
- Commands are case-insensitive: `/CK:SAVE`, `/ck:save`, `/Ck:Save` all work.
- If a script exits with code 1, display its stdout as an error message.
- Never edit `context.json` or `CONTEXT.md` directly — always use the scripts.
- If `projects.json` is malformed, tell the user and offer to reset it to `{}`.
Pliki w paczce (10)
  • SKILL.md 6 KB
  • commands/forget.mjs 1 KB
  • commands/info.mjs 1 KB
  • commands/init.mjs 6 KB
  • commands/list.mjs 1 KB
  • commands/migrate.mjs 7 KB
  • commands/resume.mjs 1 KB
  • commands/save.mjs 7 KB
  • commands/shared.mjs 15 KB
  • hooks/session-start.mjs 9 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · ginaservice/ginaservice-skills100MIT
affaan-m/ECC100MIT
SHRIJANAGAIN/Nemo-Cli100Apache-2.0

Migawka bazy z 13.11.2026 · wersja paczki e44e3498c43c (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

  • 96context-memory-keeper
    Prowadzi trwałą pamięć projektu między sesjami: zapisuje reguły, decyzje i listę zadań, by wrócić po kompresji rozmowy.
  • 90project-memory
    Prowadzi trwałą pamięć projektu w repozytorium: kontekst między sesjami, historię incydentów, decyzje i stan agentów w Claude, Codex i innych sesjach.
  • 90onboarding
    Zbiera kontekst projektu przy starcie sesji: instrukcje, stan gita, otwarte zgłoszenia i kolejne kroki.
  • 100claude-mem
    Utrzymuje trwałą pamięć w plikach między sesjami: katalog memory z decisions.md, context.md, glossary.md i sesjami z datą, wczytuje stan na starcie, dopisuje decyzje na końcu, kompaktuje co miesiąc i odrzuca sekrety.
  • 100open-session
    Otwiera lub wznawia sesję Claude Code innego folderu projektu na tym komputerze, z włączonym Remote Control, wybierając z numerowanych list.
  • 100claude-mem
    Kompresuje rozmowy i kontekst projektu w zwięzłe migawki pamięci dla Claude Code, zachowujące decyzje między sesjami i zespołami.

Uwagi i zgłoszenia

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