Agent Builder
shareAI-lab/learn-claude-code
Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.
Agent skill
Agentic Engineering Workflow
by pawel-cell in pawel-cell/micky-podcast-agentic-engineering
A skill your agent uses when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding.
Install Agentic Engineering Workflow
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering agentic-engineering-workflow --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agentic-engineering-workflow .claude/skills/agentic-engineering-workflow && rm -rf skills-srcUse ~/.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/
Install the "agentic-engineering-workflow" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/agentic-engineering-workflow into .claude/skills/agentic-engineering-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-engineering-workflow", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/agentic-engineering-workflowType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering agentic-engineering-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agentic-engineering-workflow .agents/skills/agentic-engineering-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agentic-engineering-workflow" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/agentic-engineering-workflow into .agents/skills/agentic-engineering-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-engineering-workflow", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering agentic-engineering-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agentic-engineering-workflow .cursor/skills/agentic-engineering-workflow && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agentic-engineering-workflow" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/agentic-engineering-workflow into .cursor/skills/agentic-engineering-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-engineering-workflow", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pawel-cell/micky-podcast-agentic-engineering.git --path skills/agentic-engineering-workflow--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering agentic-engineering-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agentic-engineering-workflow .gemini/skills/agentic-engineering-workflow && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agentic-engineering-workflow" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/agentic-engineering-workflow into .gemini/skills/agentic-engineering-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-engineering-workflow", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering agentic-engineering-workflowInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agentic-engineering-workflow .github/skills/agentic-engineering-workflow && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agentic-engineering-workflow" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/agentic-engineering-workflow into .github/skills/agentic-engineering-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-engineering-workflow", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pawel-cell/micky-podcast-agentic-engineering agentic-engineering-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawel-cell/micky-podcast-agentic-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agentic-engineering-workflow .opencode/skills/agentic-engineering-workflow && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agentic-engineering-workflow" agent skill from https://github.com/pawel-cell/micky-podcast-agentic-engineering/tree/main/skills/agentic-engineering-workflow into .opencode/skills/agentic-engineering-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-engineering-workflow", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agentic-engineering-workflow- GitHub stars
- 141
- Token cost
- ~1.2k tokens
- SKILL.md length
- 561 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding.
- Works in 8 steps: Pick the strongest harness/model you can… → Keep the task small. Ask for one… → Give source code as context when docs… → …
- Building software with AI agents and you need a serious end-to-end workflow instead of vibe coding
- SKILL.md covers Overview, When to Use, Workflow and Copy-Paste Starter Prompt, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Agentic Engineering Workflow is an agent skill from pawel-cell/micky-podcast-agentic-engineering. Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding. Covers harness choice, context discipline, cleanup, review loops, launch pressure, and security basics.
Its SKILL.md is about 1.2k 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 AI & LLM Engineering. The repository describes itself as: Micky podcast agentic engineering workflow bundle. The licence is MIT.
When your agent uses it
- Building software with AI agents and you need a serious end-to-end workflow instead of vibe coding
Example prompts
- “/agentic-engineering-workflow”
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Pick the strongest harness/model you can access. The harness is the wrapper around the model: file search, terminal, browser, tools…
- Keep the task small. Ask for one feature, one fix, or one reviewable unit at a time. If a plan is too large, ask the agent to split it…
- Give source code as context when docs are not enough. If you are using a package, SDK, framework, or open-source tool, put its source in a…
- Build the minimal feature first. Do not refactor the whole app while building the feature. Get the smallest working version running.
- Run a cleanup pass. After the feature works, ask the agent to find duplicated runtime mechanics and move them into reusable service-layer…
- Run a review-fix loop. Use tests, typechecks, and AI/human review. Feed review feedback back into the coding agent. Keep fixing until the…
- Launch earlier than feels comfortable. Do not hide forever behind "one more feature." A semi-functional MVP with feedback beats a perfect…
- Apply security guardrails. Use 2FA, a password manager, avoid young packages, and ask your agent to check whether your project is exposed…
What it can do on your machine
Read from SKILL.md and the folder at commit ac337fe. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
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
Agentic Engineering Workflow loads about 1.2k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 561 words of instructions outside code blocks.
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 pawel-cell/micky-podcast-agentic-engineering at commit ac337fe, republished under its MIT licence (© pawel-cell). 561 words, ~1,167 tokens.
Download SKILL.mdSave it as
.claude/skills/agentic-engineering-workflow/SKILL.md (or your agent's skills folder).- name
- agentic-engineering-workflow
- description
- Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding. Covers harness choice, context discipline, cleanup, review loops, launch pressure, and security basics.
- version
- 1.0.0
- author
- David Ondrej / Michael Shimeles interview notes
- license
- MIT
Agentic Engineering Workflow
Overview
Use this as the high-level operating system for building with AI agents. The core idea is simple: stay in charge, keep the agent's context focused, and give it tight feedback loops.
This is not "ask the AI to build everything and hope." It is a workflow where the human decides the outcome, the agent does the mechanical work, and tests/reviews keep the result honest.
When to Use
- You are building an MVP, feature, internal tool, or AI-assisted product.
- You want a repeatable AI coding workflow instead of random prompting.
- You are non-technical or early technical and need simple rules for staying in control.
- You are using Cursor, Claude Code, Codex, Hermes, or another coding harness.
Do not use this for one-off tiny edits where a normal direct prompt is enough.
Workflow
Pick the strongest harness/model you can access. The harness is the wrapper around the model: file search, terminal, browser, tools, system prompt, and project memory. The model matters, but the harness determines what the model can actually do.
Keep the task small. Ask for one feature, one fix, or one reviewable unit at a time. If a plan is too large, ask the agent to split it into smaller PR-sized chunks.
Give source code as context when docs are not enough. If you are using a package, SDK, framework, or open-source tool, put its source in a reference folder and tell the agent to search it before coding.
Build the minimal feature first. Do not refactor the whole app while building the feature. Get the smallest working version running.
Run a cleanup pass. After the feature works, ask the agent to find duplicated runtime mechanics and move them into reusable service-layer modules.
Run a review-fix loop. Use tests, typechecks, and AI/human review. Feed review feedback back into the coding agent. Keep fixing until the PR is clean or a human decision is needed.
Launch earlier than feels comfortable. Do not hide forever behind "one more feature." A semi-functional MVP with feedback beats a perfect private project.
Apply security guardrails. Use 2FA, a password manager, avoid young packages, and ask your agent to check whether your project is exposed when a package/security issue trends.
Show full SKILL.md (185 more words)Show less
Copy-Paste Starter Prompt
We are going to build this using an agentic engineering workflow.
Rules:
1. Keep the change small and reviewable.
2. Search the existing code before creating new abstractions.
3. If using a package/framework, reference its local source or official repo before guessing APIs.
4. Build the minimal working version first.
5. After it works, run a code-structure cleanup pass.
6. Run relevant tests/typechecks.
7. Summarize what changed, what was tested, and what still needs human judgment.
Task:
<describe the feature or fix here>Security Guardrails
- Never install a package that is less than 14 days old unless a human explicitly approves it.
- Use 2FA through an authenticator app, not SMS.
- Use a password manager.
- Do not paste secrets into prompts or screenshots.
- When a package breach trends, ask the agent to inspect your local projects for that package/version.
Common Pitfalls
- Letting the agent think for you. The agent is a worker, not the product owner.
- Overloading context. More context is not always better. Give the exact files/folders it needs.
- Huge PRs. Review loops break down when the diff is thousands of lines.
- No cleanup pass. Working code can still be duplicated and hard for future agents to debug.
- Never launching. Waiting for perfect is how competitors ship before you.
Verification Checklist
- Task was split into a small reviewable unit.
- Agent searched relevant existing code before editing.
- External package/framework behavior was checked against source or official docs.
- Feature works locally.
- Cleanup pass removed obvious duplication.
- Tests/typechecks ran or the reason they could not run is stated.
- Security-sensitive changes were explicitly reviewed.
© pawel-cell, 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 skills/agentic-engineering-workflow of pawel-cell/micky-podcast-agentic-engineering.
Open the folder on GitHubat commit ac337fe
Compare with similar skills
Agentic Engineering Workflow 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agentic Engineering Workflow this skillpawel-cell/micky-podcast-agentic-engineering | 141 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Agent BuildershareAI-lab/learn-claude-code | 78k | 6 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| Peft Fine TuningOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.3k | Automated safety check: Pass | MIT | |
| 1passwordtrpc-group/trpc-agent-go | 1.8k | 15 repos | ~656 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
Peft Fine Tuning
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
1password
trpc-group/trpc-agent-go
Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.
Chroma Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
More from pawel-cell/micky-podcast-agentic-engineering
Grep Loop Review Workflow
pawel-cell/micky-podcast-agentic-engineering
A skill your agent uses when you have a small PR or feature and want an agent to repeatedly fix review feedback until tests pass and the PR is merge-ready.
Source Code Context
pawel-cell/micky-podcast-agentic-engineering
A skill your agent uses when an AI coding agent is guessing API names or framework behavior from incomplete docs.
Code Structure Cleanup
pawel-cell/micky-podcast-agentic-engineering
Use after an AI-built feature works but the code has duplicated mechanics, repeated API calls, or messy structure.
Related
Categories
Questions about Agentic Engineering Workflow
What does Agentic Engineering Workflow do?
A skill your agent uses when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding. Agentic Engineering Workflow is an agent skill from pawel-cell/micky-podcast-agentic-engineering. Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding.
When should I use Agentic Engineering Workflow?
Agentic Engineering Workflow fits situations like: building software with AI agents and you need a serious end-to-end workflow instead of vibe coding.
How do I install Agentic Engineering Workflow in Claude Code?
Run `npx skills add pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a claude-code`. Or copy the skill folder (skills/agentic-engineering-workflow in pawel-cell/micky-podcast-agentic-engineering) into .claude/skills/agentic-engineering-workflow in your project. Claude Code loads it when a task matches its description.
How do I install Agentic Engineering Workflow in Codex?
Run `npx skills add pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a codex`. Or copy the skill folder (skills/agentic-engineering-workflow in pawel-cell/micky-podcast-agentic-engineering) into .agents/skills/agentic-engineering-workflow in your project. Codex loads it when a task matches its description.
Can I use Agentic Engineering Workflow 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 pawel-cell/micky-podcast-agentic-engineering --skill agentic-engineering-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentic-engineering-workflow, .gemini/skills/agentic-engineering-workflow, .github/skills/agentic-engineering-workflow and .opencode/skills/agentic-engineering-workflow in your project.
What does Agentic Engineering Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Agentic Engineering Workflow is instructions for the agent only.
Does Agentic Engineering Workflow 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 Agentic Engineering Workflow 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 Agentic Engineering Workflow use?
Agentic Engineering Workflow is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agentic Engineering Workflow use?
About 1.2k tokens (SKILL.md is roughly 4.7k 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 Agentic Engineering Workflow?
Skills that share tags, products or a category with Agentic Engineering Workflow: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agentic Engineering Workflow?
pawel-cell (a GitHub user) maintains it in pawel-cell/micky-podcast-agentic-engineering, which has 141 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on May 19, 2026.
Source: pawel-cell/micky-podcast-agentic-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.