Agent skill

Remember

by commercetools in commercetools/ui-kit

Persist guidelines, conventions, and architectural decisions into the repository's knowledge base.

MITAuto-check: notesKnowledge Management

Install Remember

skills CLI
$ npx skills add commercetools/ui-kit --skill remember -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install commercetools/ui-kit remember --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/commercetools/ui-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/remember .claude/skills/remember && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
remember
GitHub stars
154
Token cost
~2k tokens
SKILL.md length
969 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Persist guidelines, conventions, and architectural decisions into the repository's knowledge base.

  • Works in 6 steps: Intent Distillation → Identify Target File → Conflict Analysis → …
  • Told to remember something for future sessions
  • SKILL.md covers Arguments, Usage Examples, Process and Guidelines
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Remember is an agent skill from commercetools/ui-kit. Persist guidelines, conventions, and architectural decisions into the repository's knowledge base. Use when told to remember something for future sessions.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering Knowledge bases and Design systems. The licence is MIT.

When your agent uses it

  • Told to remember something for future sessions
  • Tasks that involve Knowledge bases
  • Tasks that involve Design systems

Example prompts

  • “/remember”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Grep, Glob, Read, Edit, Write

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Intent Distillation
  2. Identify Target File
  3. Conflict Analysis
  4. Write the Update
  5. Skill Discovery and Synchronization
  6. Final Confirmation

What it can do on your machine

Read from SKILL.md and the folder at commit 62ca335. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Grep
    • Glob
    • Read
    • Edit
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Remember loads about 2k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 969 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Grep, Glob, Read, Edit, Write

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from commercetools/ui-kit at commit 62ca335, republished under its MIT licence (© commercetools). 969 words, ~2,005 tokens.

Download SKILL.mdSave it as .claude/skills/remember/SKILL.md (or your agent's skills folder).
name
remember
description
Persist guidelines, conventions, and architectural decisions into the repository's knowledge base. Use when told to remember something for future sessions.
allowed-tools
Bash, Grep, Glob, Read, Edit, Write
disable-model-invocation
false
argument-hint
<guideline, convention, or architectural decision to persist>
scope
knowledge

Remember

Persist new guidelines, best practices, or architectural decisions into the repository's knowledge base so they are available in future AI sessions.

Arguments

  • thing to remember (required): A guideline, convention, or decision to persist. Natural language input describing what should be remembered.

Usage Examples

  • /remember always use the --frozen-lockfile flag in CI
  • /remember the auth module was refactored to use middleware in PR #342
  • /remember integration tests must hit a real database, never use mocks

Process

1. Intent Distillation
  • Identify the core principle, rule, or technical intent from the user's input
  • Rephrase concisely using precise software development terminology
2. Identify Target File

Determine which file should contain this knowledge. Repositories follow a layered structure, preferring tool-agnostic paths when they exist:

Intent typePreferred targetFallback
Project-wide convention or standardAGENTS.mdCLAUDE.md
Domain-specific best practice (testing, components, API design, etc.)rules/ or docs/conventions/See resolution rules
Change to an automated workflow or skill.agents/skills/.claude/skills/
Agent behavior guideline.agents/agents/.claude/agents/
Claude-specific configuration (MCP, hooks, permissions)CLAUDE.md—

Resolution rules:

  1. Check whether rules/ or docs/conventions/ exists
  2. If both exist, prefer rules/
  3. If only one exists, write there
  4. If only docs/conventions/ exists, ask the user whether they want to create a symlink from rules/ to docs/conventions/ so both paths resolve to the same location. If they confirm, create the symlink before writing.
  5. If neither exists, create rules/ and write there
  6. For other target types:
    • For .agents/skills/ or .agents/agents/: Use the .claude/ equivalent if the .agents/ directory does not exist
    • For AGENTS.md: Use CLAUDE.md if AGENTS.md does not exist
  7. Only write to CLAUDE.md or .claude/ directly when the information is Claude-specific or no tool-agnostic target exists
3. Conflict Analysis
  • Thoroughly scan the identified file(s) for any existing content that contradicts the new intent
  • Additionally, scan the corresponding file in the other layer (e.g., if writing to AGENTS.md, also scan CLAUDE.md and vice versa). If the other layer contains conflicting or duplicated content, resolve it by replacing that content in CLAUDE.md with a reference to AGENTS.md (e.g., "See AGENTS.md for project conventions.")
  • A contradiction is any statement that would be invalidated or made obsolete by the new guideline

If a conflict is found:

  • Halt execution immediately
  • Quote the exact conflicting statement(s) from the document
  • Inform the user about the contradiction and ask for clarification on how to proceed
  • Do NOT proceed with any updates until the conflict is resolved

If no conflicts are found:

  • Identify the most logical section within the file to add the new information
  • If no suitable section exists, create a new one with an appropriate heading
  • Refactor existing content as needed to keep the document coherent and well-structured
4. Write the Update

When writing the update:

  • Only include production-ready patterns and examples that can be safely copied. Use precise, declarative language. Do not include anti-patterns or cautionary examples.
Show full SKILL.md (496 more words)Show less
5. Skill Discovery and Synchronization

After successfully updating documentation, discover which skills may need updates by scanning skill files in .agents/skills/*/SKILL.md and .claude/skills/*/SKILL.md (whichever exist). When reading skill files, resolve symlinks to access the actual content rather than treating symlinks as empty or opaque files.

Discovery criteria — a skill is affected if it contains:

  • Explicit references to the updated documentation file
  • Content that covers the same topic or concept as the update
  • Inline templates, code examples, or patterns related to the updated guideline
  • Instructions or rules that may now be outdated or contradicted by the new documentation

If no skills are affected, skip this step.

For each affected skill, determine whether it is local or shared:

A skill is shared if it is a symlink pointing outside the current repo or was installed by a package manager and has not been modified locally. A skill is local if it was authored or edited in this repo. Symlinks between .claude/skills/ and .agents/skills/ within the same repo are internal bridges and do not affect this determination.

Local skills — edit directly:

  • Update the skill's templates, examples, and instructions to align with the new documentation

Shared skills — report and offer to update:

  • Report the affected shared skill and the specific inconsistency to the user

  • Ask: "Shared skill <skill-name> is affected. Add repo-specific additions?"

  • If the user confirms:

    1. Resolve the original shared skill path (the symlink target or CLI cache location where the shared skill was installed)

    2. Determine which layer to use:

      If .agents/skills/ directory exists:

      Create or update .agents/skills/<skill-name>/SKILL.md with repo-specific additions listed before the shared skill reference, so local rules take priority:

      markdown
      ---
      name: <skill-name>
      description: <same description as the shared skill>
      allowed-tools: <same allowed-tools as the shared skill>
      ---
      
      ## Repo-specific additions
      
      - <the new convention or guideline>
      
      ## Shared skill
      
      Read and follow the shared skill at `<original-shared-skill-path>`.

      Then ensure .claude/skills/<skill-name>/SKILL.md is a symlink to .agents/skills/<skill-name>/SKILL.md:

      • If it is already a symlink to the correct path, no action needed
      • If it exists as a regular file, delete it and create the symlink
      • If it does not exist, create the symlink

      If .agents/skills/ directory does not exist:

      Create or update .claude/skills/<skill-name>/SKILL.md directly with the same structure (repo-specific additions before the shared skill reference).

  • If the user declines, log the inconsistency in the final confirmation but take no action

6. Final Confirmation

Report all changes made:

  • Documentation file(s) updated
  • Skill file(s) updated (if any), with rationale explaining why each skill was identified as affected
  • Summary of what was added or modified in each file

Guidelines

  • Always read target files before modifying them
  • Prefer adding to an existing section over creating a new one
  • Keep entries concise; one to two sentences per guideline is ideal
  • If the user's input is ambiguous, ask for clarification before writing
  • Do not duplicate information that already exists in the target file
  • When creating skill files, create the <skill-name>/ subdirectory if needed but do NOT create .agents/ or .agents/skills/ directories — only use them if they already exist

© commercetools, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/remember of commercetools/ui-kit.

Open the folder on GitHubat commit 62ca335

Compare with similar skills

Remember next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Remember compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Remember this skillcommercetools/ui-kit154—~2kAutomated safety check: NotesMIT
Extracting Design Systemnoemuch/bridge156—~1.8kAutomated safety check: PassMIT
Skill Developmentletta-ai/skills147—~941Automated safety check: PassMIT
Work Operating ModelNateBJones-Projects/OB14.7k—~2.2kAutomated safety check: PassCustom licence
Memory ImportPrismer-AI/PrismerCloud1.6k—~665Automated safety check: PassMIT
TalkAbilityai/cornelius109—~834Automated safety check: PassMIT

Similar skills

  • A skill your agent uses when the user says "setup", "setup bridge", "extract", "extract DS", "onboard", "build knowledge base", "initialize bridge", or is starting Bridge in a project for the first…

    156 GitHub stars~1.8k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed
  • Skill Development

    letta-ai/skills

    Create and contribute skills to the communal knowledge base.

    147 GitHub stars~941 tokensUpdated 6 days ago
    Knowledge ManagementAuto-check passed
  • Work Operating Model

    NateBJones-Projects/OB1

    Conversation-first workflow for turning tacit work patterns into a structured operating model.

    4.7k GitHub stars~2.2k tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • Memory Import

    Prismer-AI/PrismerCloud

    Bulk-import an external knowledge base into Prismer memory via the three-layer import pipeline (07 §3.1).

    1.6k GitHub stars~665 tokensUpdated 7 days ago
    Knowledge ManagementAuto-check passed
  • Talk

    Abilityai/cornelius

    Conversational partner mode - delegates each exchange to the thinking-partner sub-agent, which embodies the knowledge base as its own memory and engages as an intellectual equal.

    109 GitHub stars~834 tokensUpdated 15 days ago
    Knowledge ManagementAuto-check passed
  • Ade Perf Boot

    arul28/ADE

    Performance patterns discovered for ADE's cold launch and "main screen" surfaces — welcome / project picker, recent projects list, project open flow, remote runtime connect, iOS pairing.

    113 GitHub stars~707 tokensUpdated today
    Knowledge ManagementAuto-check passed

More from commercetools/ui-kit

All 11 skills in this repo
  • Agent Restore Context

    commercetools/ui-kit

    Manage restore context files so skills can survive /clear and /compact.

    154 GitHub stars~944 tokensUpdated 4 days ago
    Auto-check: notes
  • Agent Restore Context Setup

    commercetools/ui-kit

    Set up the restore-context hook so skills can resume workflows after /clear and /compact.

    154 GitHub stars~1.4k tokensUpdated 4 days ago
    Auto-check: notes
  • PR Review Navigator

    commercetools/ui-kit

    Generate AI-assisted navigation aids to help humans start reviewing a pull request more efficiently.

    154 GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check: notes
  • Renovate Review

    commercetools/ui-kit

    Review Renovate dependency upgrade PRs to assess safety and effort.

    154 GitHub stars~907 tokensUpdated 4 days ago
    Auto-check: notes
  • Repo Healthcheck Node

    commercetools/ui-kit

    Verify a Node.js/TypeScript repo's development environment is correctly set up.

    154 GitHub stars~1.6k tokensUpdated 4 days ago
    Auto-check: notes
  • Repo Maintenance Node

    commercetools/ui-kit

    Perform a broad Node/TypeScript repository health sweep — formatting, linting, type errors, dead code, dependency hygiene, and open Renovate PRs.

    154 GitHub stars~3k tokensUpdated 4 days ago
    Auto-check: notes

Questions about Remember

What does Remember do?

Persist guidelines, conventions, and architectural decisions into the repository's knowledge base. Remember is an agent skill from commercetools/ui-kit. Persist guidelines, conventions, and architectural decisions into the repository's knowledge base.

When should I use Remember?

Remember fits situations like: told to remember something for future sessions; tasks that involve Knowledge bases; tasks that involve Design systems.

How do I install Remember in Claude Code?

Run `npx skills add commercetools/ui-kit --skill remember -a claude-code`. Or copy the skill folder (.agents/skills/remember in commercetools/ui-kit) into .claude/skills/remember in your project. Claude Code loads it when a task matches its description.

How do I install Remember in Codex?

Run `npx skills add commercetools/ui-kit --skill remember -a codex`. Or copy the skill folder (.agents/skills/remember in commercetools/ui-kit) into .agents/skills/remember in your project. Codex loads it when a task matches its description.

Can I use Remember in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add commercetools/ui-kit --skill remember -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/remember, .gemini/skills/remember, .github/skills/remember and .opencode/skills/remember in your project.

What does Remember need to run?

SKILL.md names no scripts, command-line tools or credentials: Remember is instructions for the agent only. Its frontmatter pre-approves these tools: Bash, Grep, Glob, Read, Edit, Write.

Does Remember access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Remember safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Remember use?

Remember is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Remember use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Remember?

Skills that share tags, products or a category with Remember: Extracting Design System (noemuch/bridge, 156 stars), Skill Development (letta-ai/skills, 147 stars), Work Operating Model (NateBJones-Projects/OB1, 4.7k stars) and Memory Import (Prismer-AI/PrismerCloud, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Remember?

commercetools (a GitHub organization) maintains it in commercetools/ui-kit, which has 154 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 3, 2026.

Source: commercetools/ui-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.