Implement a planned DynamoDB-Toolbox feature end-to-end and open a pull request.

MITAuto-check passedDatabases

Install Implement

skills CLI
$ npx skills add dynamodb-toolbox/dynamodb-toolbox --skill implement -a claude-code

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

GitHub CLI
$ gh skill install dynamodb-toolbox/dynamodb-toolbox implement --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/dynamodb-toolbox/dynamodb-toolbox.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/implement .claude/skills/implement && 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
implement
GitHub stars
2k
Token cost
~1.8k tokens
SKILL.md length
1,067 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Implement a planned DynamoDB-Toolbox feature end-to-end and open a pull request.

  • Works in 8 steps: Read the tasks → Explore the codebase → Implement in reviewable chunks → …
  • Tasks that involve NoSQL databases
  • SKILL.md covers Context, Your task and Workflow feedback
  • Calls npm and git

What it does

Implement is an agent skill from dynamodb-toolbox/dynamodb-toolbox. Implement a planned DynamoDB-Toolbox feature end-to-end and open a pull request. Invoke with /implement.

Its SKILL.md is about 1.8k 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 Databases, covering NoSQL databases. It works with Amazon DynamoDB, Amazon Web Services and TypeScript. The repository describes itself as: Lightweight and type-safe query builder for DynamoDB and TypeScript. The licence is MIT.

When your agent uses it

  • Tasks that involve NoSQL databases

Example prompts

  • “/implement”

Workflow steps

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

  1. Read the tasks
  2. Explore the codebase
  3. Implement in reviewable chunks
  4. Update /docs/
  5. Self-review
  6. Invite the user to read the updates
  7. Create the PR
  8. Update Notion

What it can do on your machine

Read from SKILL.md and the folder at commit 551a4d8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use npm and git, which can reach the network depending on how they are called.

    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

Implement loads about 1.8k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 1,067 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 passed

The automated check found no risky patterns in SKILL.md.

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 dynamodb-toolbox/dynamodb-toolbox at commit 551a4d8, republished under its MIT licence (© dynamodb-toolbox). 1,067 words, ~1,752 tokens.

Download SKILL.mdSave it as .claude/skills/implement/SKILL.md (or your agent's skills folder).
name
implement
description
Implement a planned DynamoDB-Toolbox feature end-to-end and open a pull request. Invoke with /implement.
disable-model-invocation
true

Coding Agent — DynamoDB-Toolbox

You are a senior software engineer for DynamoDB-Toolbox, an open source lightweight and type-safe query builder for DynamoDB.

The product spec and technical strategy have already been written and approved. Your job is to implement the feature exactly as described, then open a pull request.

Context

Before writing any code, read the following:

  • /CLAUDE.md — architecture, conventions, coding standards, and PR process

Your task

Step 1 — Read the tasks

List the tasks that are in To Implement status. If there are none, stop there. If there are several, ask which task you should handle.

As soon as the task is chosen, set its status to Implementing before any other work, so parallel /implement runs don't grab the same task.

Fetch the full Notion task, read both the spec and the Strategy section. Extract:

  • The acceptance criteria from the spec
  • The ordered implementation steps and delivery chunks from the Strategy section
  • The list of affected files
  • All edge cases and their technical handling
Step 2 — Explore the codebase

Before writing any code:

  • Check that you're on the main branch. If you're not, warn the developer and wait for them to tell you to go ahead.
  • Read every file listed in "Affected components".
  • Understand the existing patterns (naming, structure, error handling, the Action pattern, type-level utilities).
  • Run the test suite to confirm it passes before you start.
  • If anything in the strategy is ambiguous or contradicts what you see in the code, stop and flag it or ask questions rather than making assumptions.
Step 3 — Implement in reviewable chunks

Implement the feature one delivery chunk at a time (the chunks laid out in the Strategy). Do not race ahead through every chunk in a single pass — a chunk is the unit the developer reviews. If the Strategy predates chunking and lists only flat steps, group them yourself into coherent milestones and proceed the same way.

For each step within the current chunk:

  • Write the code, following existing conventions exactly — do not introduce new patterns unless the strategy explicitly calls for it.
  • Follow the Action pattern: prefer a new actions/<name>/ folder over adding a method to a core class.
  • Re-export new public API from src/index.ts and add the matching subpath to package.json exports.
  • Handle every edge case listed in the spec.
  • Do not touch files outside the scope defined in "Affected components" unless strictly necessary — if you do, explain why in the PR description.
  • Format the code.

At the end of each chunk, before starting the next:

  • Verify it — run the relevant tests/build (npm run test-type, npm run test-unit filtered to the folder, then the full npm test when the chunk warrants it) and confirm it's green wherever possible; call out anything left red mid-migration.
  • Summarise what changed, what's verified, and any caveat carried forward — keep it skimmable.
  • Pause and wait for the developer to review. Do not begin the next chunk until they tell you to continue. (Committing still follows the hard rule in Step 6 — only on an explicit request.)

Coding standards:

  • See /CLAUDE.md (ESLint, Prettier, naming conventions, .js import extensions, ~/* path alias).
  • No dead code, no commented-out blocks, no console.log left in.
Clarity over comments

Make the code readable on its own instead of annotating it. Prefer clear names, small coherent functions, and obvious control flow so the intent is visible without narration.

Add a comment only where the code cannot be made self-explanatory — an opaque workaround, a type-system quirk, a non-obvious constraint or ordering requirement. State the why, not the what. A comment that restates what the code already says is noise — delete it. When tempted to explain a block, first try to make it clearer (rename, extract, simplify); comment only if it still needs it.

Show full SKILL.md (448 more words)Show less
Compact the conversation regularly

A full feature spans many files and long tool outputs, so context fills up fast. Compact roughly every 50k tokens — a natural moment is a chunk boundary (Step 3's pause), once the chunk's work is verified and summarised. Run /compact with a short instruction to keep what still matters (the ticket, the delivery-chunk list and which chunk is next, the branch name, any caveat carried forward) and drop the rest. Compacting at a chunk boundary is cheap because the durable state already lives in the summary you just wrote; compacting mid-chunk risks losing in-flight detail, so finish the chunk first.

Step 4 — Update /docs/

Update the relevant file(s) in /docs/docs/ to reflect the new or changed feature. Each schema type and action has a corresponding page. This is not optional — it is part of the definition of done. The task should already list the updates to do.

Step 5 — Self-review

Go through this checklist:

  • All acceptance criteria from the spec are met
  • All edge cases are handled
  • No files modified outside the defined scope (or justified if so)
  • New public API re-exported from src/index.ts and given a package.json subpath
  • Tests written and passing (unit + type)
  • No debug code left in
  • No unintended behaviour changes to existing features
  • Docs updated
Step 6 — Invite the user to read the updates

The developer can take over and manually edit the generated code. Wait for them to tell you to continue.

Hard rule — no shipping without an explicit order. Never run git commit, git push, or create a PR unless the developer has explicitly asked in their latest message. This applies at every point in the flow, not just here:

  • A "go" or approval covers only the actions you announced right before it — it is not a standing authorization.
  • If the developer manually edits files at any point (including after a commit or push), commit and push those edits yourself.
  • When in doubt, show the diff and ask.
Step 7 — Create the PR

Once the developer explicitly asks you to commit and open the PR:

  • Create a branch named feature/$TICKET_ID-short-description off main.
  • Run the full test suite (npm test). If any test fails, fix it before proceeding. Do not open a PR with a failing suite.
  • Generate the pull request — check /CLAUDE.md for PR conventions.
Step 8 — Update Notion

Update the Notion task:

  • Fill the GitHub PR property with the PR URL
  • Update the status to Reviewing.

Workflow feedback

Once the PR is opened, run the shared feedback loop in ../../workflow-feedback.md: ask the developer for feedback on this /implement workflow itself and — if they have any and approve the changes — open a small PR improving the workflow prompts.

© dynamodb-toolbox, 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 .claude/skills/implement of dynamodb-toolbox/dynamodb-toolbox.

Open the folder on GitHubat commit 551a4d8

Compare with similar skills

Implement 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.

Implement compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implement this skilldynamodb-toolbox/dynamodb-toolbox2k—~1.8kAutomated safety check: PassMIT
AWS Dynamodbalinaqi/maggy707—~4.6kAutomated safety check: PassMIT
Amplify Workflowawslabs/agent-plugins912—~3.2kAutomated safety check: PassApache-2.0
AWS Amplifyaws/agent-toolkit-for-aws2.8k—~3.9kAutomated safety check: PassApache-2.0
Dynamodbitsmostafa/aws-agent-skills1.2k—~2.5kAutomated safety check: PassMIT
AWS CLI Beastgiuseppe-trisciuoglio/developer-kit355—~1.7kAutomated safety check: NotesMIT

Similar skills

  • AWS Dynamodb

    alinaqi/maggy

    AWS DynamoDB single-table design, GSI patterns, SDK v3 TypeScript/Python

    707 GitHub stars~4.6k tokensUpdated 13 days ago
    DatabasesAuto-check passed
  • Amplify Workflow

    awslabs/agent-plugins

    Official

    Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first).

    912 GitHub stars~3.2k tokensUpdated yesterday
    MobileAuto-check passed
  • AWS Amplify

    aws/agent-toolkit-for-aws

    Official

    Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first).

    2.8k GitHub stars~3.9k tokensUpdated today
    MobileAuto-check passed
  • Dynamodb

    itsmostafa/aws-agent-skills

    AWS DynamoDB NoSQL database for scalable data storage. An agent skill from itsmostafa/aws-agent-skills.

    1.2k GitHub stars~2.5k tokensUpdated yesterday
    DatabasesAuto-check passed
  • AWS CLI Beast

    giuseppe-trisciuoglio/developer-kit

    Provides advanced AWS CLI patterns for managing EC2, Lambda, S3, DynamoDB, RDS, VPC, IAM, and CloudWatch.

    355 GitHub stars~1.7k tokensUpdated 27 days ago
    DatabasesAuto-check: notes
  • Ak Dev New Multimodal Storage

    yaalalabs/agent-kernel

    Step-by-step guide for adding a new multimodal attachment storage backend to Agent Kernel.

    191 GitHub stars~4.3k tokensUpdated today
    DatabasesAuto-check passed

More from dynamodb-toolbox/dynamodb-toolbox

  • Plan

    dynamodb-toolbox/dynamodb-toolbox

    Write the technical implementation strategy for a spec'd DynamoDB-Toolbox task.

    2k GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check passed
  • Spec

    dynamodb-toolbox/dynamodb-toolbox

    Formalise a product spec for a DynamoDB-Toolbox task — interview, codebase analysis, and Notion write-back.

    2k GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed

Categories

Questions about Implement

What does Implement do?

Implement a planned DynamoDB-Toolbox feature end-to-end and open a pull request. Implement is an agent skill from dynamodb-toolbox/dynamodb-toolbox. Implement a planned DynamoDB-Toolbox feature end-to-end and open a pull request.

When should I use Implement?

Implement fits situations like: tasks that involve NoSQL databases.

How do I install Implement in Claude Code?

Run `npx skills add dynamodb-toolbox/dynamodb-toolbox --skill implement -a claude-code`. Or copy the skill folder (.claude/skills/implement in dynamodb-toolbox/dynamodb-toolbox) into .claude/skills/implement in your project. Claude Code loads it when a task matches its description.

How do I install Implement in Codex?

Run `npx skills add dynamodb-toolbox/dynamodb-toolbox --skill implement -a codex`. Or copy the skill folder (.claude/skills/implement in dynamodb-toolbox/dynamodb-toolbox) into .agents/skills/implement in your project. Codex loads it when a task matches its description.

Can I use Implement 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 dynamodb-toolbox/dynamodb-toolbox --skill implement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/implement, .gemini/skills/implement, .github/skills/implement and .opencode/skills/implement in your project.

What does Implement need to run?

Going by SKILL.md and its folder, Implement needs the command-line tools its instructions call (npm and git).

Does Implement access the network?

SKILL.md contains no URLs. Its commands use npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Implement safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Implement use?

Implement 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 Implement use?

About 1.8k tokens (SKILL.md is roughly 7k 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 Implement?

Skills that share tags, products or a category with Implement: AWS Dynamodb (alinaqi/maggy, 707 stars), Amplify Workflow (awslabs/agent-plugins, 912 stars), AWS Amplify (aws/agent-toolkit-for-aws, 2.8k stars) and Dynamodb (itsmostafa/aws-agent-skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implement?

dynamodb-toolbox (a GitHub organization) maintains it in dynamodb-toolbox/dynamodb-toolbox, which has 2,002 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 3, 2026.

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