SKILLEMALL.ai
GitHub ↗ RU Sign in

BC ck

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.

The skillemall take

Promises to preserve project memory across Claude Code sessions via Node.js commands and a SessionStart hook. Contains 10 files, 9 scripts covering init, save, resume, info, list, forget, and v1-to-v2 migration. Sandbox showed scripts stay within their directories, no critical issues found. Quality 83, process 56—files are clean, but actual command logic needs testing in a real project.

Catch: relies on Node.js environment and filesystem access, which isn't available everywhere (Cursor, Copilot have different setups). Works for Claude Code and Codex; other platforms in the list may fail silently. Install if you're on Claude Code and juggling projects where context window runs out.

affaan-m/everything-claude-code Agent Skills author: affaan-m MIT 10 files · 9 scripts body ≈ 1 093 tokens Open the sourcegithub.com↗ analyzed 24 h ago

Persistent per-project memory for Claude Code (Context Keeper) driven by deterministic Node.js /ck commands: init, save, resume, info, list, forget, and…

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
83
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 0

    ✓ No critical or high findings

    Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "repo"

    Process rating: all ten parameters 56/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 3 mutating operations with no state check
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 65Failures and branches. 3 branches
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 11 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1093 tokens
    • 100Progress reporting. Reports progress

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 426: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 11 items
    • +4Has examples (12 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    In the sandbox The scripts kept to themselves

    The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

    Запущено 9 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

    commands/forget.mjsничего за пределами своей папки
    commands/info.mjsничего за пределами своей папки
    commands/init.mjsничего за пределами своей папки
    commands/list.mjsничего за пределами своей папки
    commands/migrate.mjsничего за пределами своей папки
    commands/resume.mjsничего за пределами своей папки
    commands/save.mjsничего за пределами своей папки
    commands/shared.mjsничего за пределами своей папки
    hooks/session-start.mjsничего за пределами своей папки

    6 Oct 2026