agentleFS
Sign inStart free
viknesh20-20viknesh20-20/claude-code-tool-kit/.claude/skills/memory/SKILL.md

memory

Skill7 starsChanged 6 months agoMITView on GitHub

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.

99 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecosystem-reference, fractal-delegation and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • Maliot100XSkill

    send-user-message

    Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp). Use when the agent needs to notify, alert, or send an unsolicited message to a user — especially during heartbeat invocations, scheduled tasks, or when the agent wants to reach out without a prior user message in the current conversation. Triggers: 'send message to user', 'notify user', 'alert user', 'message the user on discord/telegram/whatsapp', or any need to proactively communicate with a paired sender.

    Also in 4 projects that use this

  • jh941213Skill

    docs-ci

    문서 CI(링크·OpenAPI lint·breaking 게이트·mermaid 검증)나 문서 드리프트 감지(docs.yaml 신선도 검사)를 설치하거나 돌릴 때 사용. 문서 내용 작성은 docs-architecture·docs-interfaces·docs-manuals.

    Also in 3 projects that use this

  • jh941213Skill

    docs-interfaces

    API·이벤트 인터페이스 문서(OpenAPI·swagger·AsyncAPI 명세, 엔드포인트 레퍼런스, API 구성도·시퀀스, API CHANGELOG)를 만들거나 코드와 맞출 때 사용. 시스템 구성도는 docs-architecture, API 설계 원칙은 api-design-principles.

    Also in 3 projects that use this

  • +6 more from naman10parikh
  • +1 more from jh941213

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 82 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which type: project / user / feedback / reference.

    line 49
  2. Distinctive:

    Ask for the title (slug becomes the filename).

    line 50
  3. Distinctive:

    Ask for the description (one line — used for relevance scoring later).

    line 51
  4. Very specific:

    Ask for the body. For project/ and feedback/, prompt for Why: and How to apply: explicitly.

    line 52
  5. Distinctive:

    Never write a memory the user didn't volunteer.

    line 85
  6. Distinctive:

    Always update over add when the topic overlaps.

    line 86
  7. Distinctive:

    Always convert relative dates to absolute.

    line 87
  8. Distinctive:

    Never put secrets, API keys, tokens, or PII into memory.

    line 88
  9. Very specific:

    Always update the MEMORY.md index when adding/removing.

    line 89

“Common” is measured: kept by at least 6 in 10 of the 82 edited versions of this file we could read. “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

/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:

  1. Ask which type: project / user / feedback / reference.
  2. Ask for the title (slug becomes the filename).
  3. Ask for the description (one line — used for relevance scoring later).
  4. Ask for the body. For project/ and feedback/, prompt for Why: and How to apply: explicitly.
  5. Show the file you're about to write. Get confirmation.
  6. Write the file.
  7. 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.

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.

Check your setup, free