- Home
- Skills
- Agents & Orchestration
- Developer Toolkit — 10 AI Coding Skills
Developer Toolkit — 10 AI Coding Skills
Complete toolkit for code review, debugging, documentation, and system architecture.
Free
Works with the AI Agents you already use
Developer Toolkit — 10 AI Coding Skills
Example session with this skill installed
Write a SQL query for PostgreSQL to find all users who signed up in the last 30 days but haven't made a purchase, joined with the 'orders' table. Here is my schema: users (id, created_at), orders (id, user_id, amount).
- Read your context and instructions
- Compiled the developer toolkit
I will generate a PostgreSQL query to identify inactive recent signups by performing a left join and filtering for null matches in the orders table.
PostgreSQL: Recent Inactive Users
-- Finds users created within the last 30 days who have no entries in the orders table.
SELECT
u.id,
u.created_at
FROM
users AS u
LEFT JOIN
orders AS o ON u.id = o.user_id
WHERE
u.created_at >= CURRENT_DATE - INTERVAL '30 days'
AND o.id IS NULL;
Query Explanation
- Dialect: PostgreSQL (uses
INTERVALsyntax for date arithmetic). - JOIN Type:
LEFT JOINis used to include all users regardless of order history. - Filter:
o.id IS NULLspecifically isolates users who do not have a corresponding record in theorderstable. - Performance: This query assumes an index on
users.created_atandorders.user_id.
Next steps
- Run
EXPLAIN ANALYZEon this query if theuserstable exceeds 100k rows to check for sequential scans. - If you need to include the count of attempted (but failed) payments, let me know to adjust the join logic.
- Add a
LIMITclause if you plan to process these users in batches for an email campaign.
Connects securely to your tools. The creator never sees your data.
About this skill
Shipping software is hard. Writing the code is only half the battle, and the other half is often a slog of documentation, debugging, and boilerplate testing. This skill package streamlines the entire development lifecycle, from initial system design to final API documentation. It provides a suite of tools for senior-level code review, systematic debugging, and writing clear project artifacts like READMEs and commit messages.
What it does
- Reviews code for security, performance, and correctness with prioritized findings.
- Debugs systematically by analyzing stack traces and generating ranked hypotheses.
- Generates documentation including API references, project READMEs, and technical explanations.
- Writes queries and patterns for SQL and Regex across multiple dialects and flavors.
- Builds test suites covering happy paths, edge cases, and error boundaries.
How it works
- Share your context by pasting a code snippet, error log, schema, or diff into the chat.
- State your goal such as "write unit tests for this," "explain this regex," or "review this PR."
- Refine the output by choosing the depth of explanation or specifying a target framework or dialect.
- Implement the results using the provided copy-pasteable code blocks, tables, and checklists.
Frameworks & tools
Supports major languages including JavaScript, Python, Go, Java, and Ruby. Integrates with testing frameworks like Jest, pytest, and JUnit, and handles SQL dialects for PostgreSQL, MySQL, and SQLite.
Why this beats prompting it yourself
Generic prompts often miss the edge cases that actually break production code. These skills use specific engineering directives to ensure API docs are runnable, regex patterns are safe, and bug fixes are verified against root causes.
Use cases
- Code reviews to catch N+1 queries or security holes before a merge.
- Project scaffolding to quickly generate professional READMEs and conventional commits.
- Legacy code analysis to explain complex functions and map data flow for new team members.
- Interview prep to practice system design with back-of-envelope estimates.
Known limitations
Does not perform live execution of code or real-time database migrations. Requires manual input of schema details if they are not present in the provided snippets.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
No live code execution or DB migrations. Requires provided context for schemas and types. Estimates are for architectural planning, not production benchmarking.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 10 days ago
- Free with an Agensi account
- Software
Python
Git