ワンクリックでManusで任意のスキルを実行

memory

スター5

フォーク0

更新日2026年5月2日 17:30

Manage the persistent memory layer in .claude/memory/ — list, search, save, update, delete, dedupe. Use to inspect what memories exist, write a new one, or clean up stale entries.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

viknesh20-20

viknesh20-20/claude-code-tool-kit

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

/memory

Operate on .claude/memory/. Memory persists across sessions and is shared across all 12 toolkit agents.

Subcommands

`list` (default)

Print the current memory index, grouped by type. One line per entry: name, description, last-verified date.

## Project (4)
- monorepo-layout — apps/, packages/, infra/. Yarn workspaces. (2026-04-18)
- billing-flag-state — webhook still off in prod, on in staging. (2026-05-01)
- migration-plan-q3 — auth migration to Lucia, target 2026-07-01. (2026-04-30)
…

## User (2)
- role — senior eng, owns the platform team. (2026-04-15)
- preferences — terse responses; no emojis; vitest over jest. (2026-04-15)

## Feedback (1)
- no-mocks-in-integration — integration tests must hit real DB. (2026-04-22)

## Reference (1)
- linear-eng-board — pipeline bugs tracked in Linear project ENG. (2026-04-15)

## Inherited (0)
## Handoffs (3)
- 2026-05-01 — auth migration shipped; billing flag pending.
- 2026-04-30 — design system v2 RFC opened.
- 2026-04-29 — initial repo onboarding.

`search <query>`

Find memories whose name, description, or body matches the query. Use to remind yourself of context before answering a related question.

`save`

Walk through writing a new memory:

Ask which type: project / user / feedback / reference.
Ask for the title (slug becomes the filename).
Ask for the description (one line — used for relevance scoring later).
Ask for the body. For project/ and feedback/, prompt for Why: and How to apply: explicitly.
Show the file you're about to write. Get confirmation.
Write the file.
Update .claude/memory/MEMORY.md index.

Frontmatter:

---
name: <title>
type: project | user | feedback | reference
description: <one-line>
created: 2026-05-02
last-verified: 2026-05-02
---

<body>

`update <name>`

Find the memory by name. Show its current contents. Ask what to change. Update the file and bump last-verified.

`delete <name>`

Find the memory. Show what would be deleted. Ask for confirmation. Delete the file and remove the line from MEMORY.md.

`dedupe`

Scan memories within each type for likely duplicates (same topic phrased differently). Surface candidates. Never auto-merge — always show pairs and ask which to keep.

Behavioral rules (enforced by the auto-loaded `memory-discipline` rule)

Never write a memory the user didn't volunteer.
Always update over add when the topic overlaps.
Always convert relative dates to absolute.
Never put secrets, API keys, tokens, or PII into memory.
Always update the MEMORY.md index when adding/removing.

Output format

For list, render the grouped index above. For search, show matching memories with their full body. For save / update / delete, show before/after diffs and confirm before writing.

このリポジトリの他の Skills

同じリポジトリ

a11y-audit

viknesh20-20/claude-code-tool-kit

Accessibility audit of UI code or a running site against WCAG 2.1 AA. Walks every WCAG criterion that maps to common patterns: keyboard reach, focus visibility, contrast, semantic HTML, ARIA, labels, alt text, motion, screen-reader sense. Severity-graded with code fixes.

2026-05-025

business-blueprint

viknesh20-20/claude-code-tool-kit

Comprehensive business-logic blueprint for SaaS, ERP, e-commerce, and marketplace applications. Walks through every domain (auth, billing, multi-tenancy, inventory, audit, compliance, etc.), surfaces the edge cases that actually break in production, and proposes a concrete plan tailored to the user's context.

2026-05-025

business-logic-audit

viknesh20-20/claude-code-tool-kit

Reviews existing business code (billing, multi-tenancy, state machines, inventory, GL postings, audit logs, etc.) for missing real-world edge cases. Severity-graded findings — invariant violations, race conditions, missing idempotency, currency precision bugs, audit gaps, jurisdiction issues.

2026-05-025

competitive-analysis

viknesh20-20/claude-code-tool-kit

Research how 2–4 mature competitors solve a specific business problem (billing, RBAC, search, onboarding, multi-tenancy, etc.) and produce a side-by-side comparison so the team can pick the right approach for their context. Uses web search + scraping; cites every source.

2026-05-025

design-flow

viknesh20-20/claude-code-tool-kit

Designs an end-to-end user flow before any pixels are drawn — entry point, screens, decisions, branches, error/recovery paths, edge cases, microcopy hooks. Outputs a structured spec engineering and design can build from.

2026-05-025

microcopy

viknesh20-20/claude-code-tool-kit

Writes or reviews UX copy — button labels, error messages, empty states, success messages, tooltips, form labels, onboarding text, confirmation dialogs. Voice-consistent, action-led, recovery-oriented. Localizable. No dark patterns.

2026-05-025

name	memory
description	Manage the persistent memory layer in .claude/memory/ — list, search, save, update, delete, dedupe. Use to inspect what memories exist, write a new one, or clean up stale entries.
argument-hint	[list \| search <query> \| save \| delete <name> \| dedupe]

/memory

Operate on .claude/memory/. Memory persists across sessions and is shared across all 12 toolkit agents.

Subcommands

`list` (default)

Print the current memory index, grouped by type. One line per entry: name, description, last-verified date.

## Project (4)
- monorepo-layout — apps/, packages/, infra/. Yarn workspaces. (2026-04-18)
- billing-flag-state — webhook still off in prod, on in staging. (2026-05-01)
- migration-plan-q3 — auth migration to Lucia, target 2026-07-01. (2026-04-30)
…

## User (2)
- role — senior eng, owns the platform team. (2026-04-15)
- preferences — terse responses; no emojis; vitest over jest. (2026-04-15)

## Feedback (1)
- no-mocks-in-integration — integration tests must hit real DB. (2026-04-22)

## Reference (1)
- linear-eng-board — pipeline bugs tracked in Linear project ENG. (2026-04-15)

## Inherited (0)
## Handoffs (3)
- 2026-05-01 — auth migration shipped; billing flag pending.
- 2026-04-30 — design system v2 RFC opened.
- 2026-04-29 — initial repo onboarding.

`search <query>`

Find memories whose name, description, or body matches the query. Use to remind yourself of context before answering a related question.

`save`

Walk through writing a new memory:

Ask which type: project / user / feedback / reference.
Ask for the title (slug becomes the filename).
Ask for the description (one line — used for relevance scoring later).
Ask for the body. For project/ and feedback/, prompt for Why: and How to apply: explicitly.
Show the file you're about to write. Get confirmation.
Write the file.
Update .claude/memory/MEMORY.md index.

Frontmatter:

---
name: <title>
type: project | user | feedback | reference
description: <one-line>
created: 2026-05-02
last-verified: 2026-05-02
---

<body>

`update <name>`

Find the memory by name. Show its current contents. Ask what to change. Update the file and bump last-verified.

`delete <name>`

Find the memory. Show what would be deleted. Ask for confirmation. Delete the file and remove the line from MEMORY.md.

`dedupe`

Scan memories within each type for likely duplicates (same topic phrased differently). Surface candidates. Never auto-merge — always show pairs and ask which to keep.

Behavioral rules (enforced by the auto-loaded `memory-discipline` rule)

Never write a memory the user didn't volunteer.
Always update over add when the topic overlaps.
Always convert relative dates to absolute.
Never put secrets, API keys, tokens, or PII into memory.
Always update the MEMORY.md index when adding/removing.

Output format

For list, render the grouped index above. For search, show matching memories with their full body. For save / update / delete, show before/after diffs and confirm before writing.

memory

/memory

Subcommands

list (default)

search <query>

save

update <name>

delete <name>

dedupe

Behavioral rules (enforced by the auto-loaded memory-discipline rule)

Output format

このリポジトリの他の Skills

このリポジトリの他の Skills

/memory

Subcommands

list (default)

search <query>

save

update <name>

delete <name>

dedupe

Behavioral rules (enforced by the auto-loaded memory-discipline rule)

Output format

`list` (default)

`search <query>`

`save`

`update <name>`

`delete <name>`

`dedupe`

Behavioral rules (enforced by the auto-loaded `memory-discipline` rule)

`list` (default)

`search <query>`

`save`

`update <name>`

`delete <name>`

`dedupe`

Behavioral rules (enforced by the auto-loaded `memory-discipline` rule)