Developer & AI Engineering Pack
A senior second pass on the work that usually ships without one — documentation, API contract testing, security scanning, RAG debugging and agent architecture.
These skills don't autocomplete for you. They apply the standard a good staff engineer would apply: what's actually wrong here, why does it matter, and what's the smallest correct fix. Each returns a structured verdict with prioritised findings, not a wall of suggestions.
For engineers working without a review partner, and for teams who want a consistent bar applied before code reaches a human reviewer. Free companion skills — Socratic Code Reviewer, TDD Loop Master and Systematic Bug Debugger — are on my profile at no cost.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 6 skills unlock instantly in your library.
What's included
6 skills
Developer documentation structured around what developers are trying to do - information architecture, quickstart, how-to guides, reference docs and a gap audit. Use when the user says nobody understands our codebase, our docs are out of date, write developer documentation, create an API quickstart guide, write a README for this library, or audit our docs for gaps.
Produces a complete AI agent scaffold — charter, system prompt, SKILL.md, tool map, guardrails, runbook, and test suite — from a one-line job description. Use when the user says "build an AI agent for X", "scaffold a new agent", "write a system prompt and SKILL.md", "design an agent's guardrails", or "make an agent workflow runbook". Do not use when the user just wants a single prompt with no full agent architecture.
Produces a diagnosis of why a RAG system gives confident-but-wrong answers, or picks between vector search, knowledge graph, and structured/temporal retrieval. Use when the user says "why is our RAG hallucinating", "diagnose this failing query", "should we use a knowledge graph", "pick a retrieval architecture", or "design our memory layer". Do not use when the request is building a RAG system from zero.
Produces a configured static analysis (SAST) setup — tool selection among Semgrep, SonarQube, or CodeQL, ruleset config, and CI gate wiring. Use when the user says "set up SAST for our codebase", "configure Semgrep rules", "tune out false positives", "wire static analysis into CI", or "pick a SAST tool for our stack". Do not use when the request is a broader security/compliance audit beyond static code analysis.
Produces an exhaustive test suite (happy-path, edge-case, negative, contract, security tests) and coverage matrix from an OpenAPI spec, or audits an existing suite for gaps. Use when the user says "generate tests from my OpenAPI spec", "test my API contract", "find gaps in my test suite", or "check contract conformance". Do not use when the user wants the API contract designed, not tested.
Produces a QA/UAT pack (acceptance criteria, UAT scripts, edge-case matrix, regression checklist) for an AI automation, or audits an existing one's test coverage. Use when the user says "write UAT for this automation", "QA this AI workflow", "find test coverage gaps", or "build a regression checklist". Do not use when the deliverable is the agent itself, not its test coverage.
See it in action
Developer Documentation Writer
Example session with this skill installed
We ship a Python SDK for our webhook signing service. Right now the only docs are a README with an auto-generated API reference. Help me structure proper developer docs.
- Read your context and instructions
- Compiled the developer documentation writer
Documentation plan for the webhook signing SDK, organised around what developers are trying to do.
Information architecture
- Quickstart: sign and verify a first webhook
- How-to guides: task-focused recipes
- Reference: the existing generated API docs, cleaned up
- Concepts: how signing works and why
Quickstart outline
pip install your-sdk
from your_sdk import verify
verify(payload, signature_header, secret)
Steps: install, set the secret as an environment variable, verify an incoming request, see what a failed check looks like.
How-to guides
- Verify webhooks in Flask, Django and FastAPI
- Rotate a signing secret without downtime
- Handle replay attacks with timestamps
- Test signature checks locally
Reference
Keep it generated, but add one example per public function and document every exception it can raise.
Gap audit
| Gap | Impact | Fix |
|---|---|---|
| No quickstart | New users read reference first | Write the quickstart |
| No framework examples | Common integrations guessed | Three how-to pages |
| Exceptions undocumented | Error handling unclear | Add to reference |
| No secret rotation guide | Risky manual process | How-to page |
Next steps
- Write the quickstart first and test it on a clean environment
- Draft the Flask and Django guides next
- Move the README content into the new structure
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 these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
1 use
Times these skills were used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.