Building Agent Systems
telagod/code-abyss
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…
Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs.
Install AI Product Management
$ npx skills add andreaskelm/pm-brain --skill ai-product-management -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install andreaskelm/pm-brain ai-product-management --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/andreaskelm/pm-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ai-product-management .claude/skills/ai-product-management && 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 "ai-product-management" agent skill from https://github.com/andreaskelm/pm-brain/tree/main/.claude/skills/ai-product-management into .claude/skills/ai-product-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-product-management", 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/andreaskelm/pm-brain/tree/main/.claude/skills/ai-product-managementType 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 andreaskelm/pm-brain --skill ai-product-management -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install andreaskelm/pm-brain ai-product-management --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/andreaskelm/pm-brain.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/ai-product-management .agents/skills/ai-product-management && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-product-management" agent skill from https://github.com/andreaskelm/pm-brain/tree/main/.claude/skills/ai-product-management into .agents/skills/ai-product-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-product-management", 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 andreaskelm/pm-brain --skill ai-product-management -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install andreaskelm/pm-brain ai-product-management --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/andreaskelm/pm-brain.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/ai-product-management .cursor/skills/ai-product-management && 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 "ai-product-management" agent skill from https://github.com/andreaskelm/pm-brain/tree/main/.claude/skills/ai-product-management into .cursor/skills/ai-product-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-product-management", 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/andreaskelm/pm-brain.git --path .claude/skills/ai-product-management--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 andreaskelm/pm-brain --skill ai-product-management -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install andreaskelm/pm-brain ai-product-management --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/andreaskelm/pm-brain.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/ai-product-management .gemini/skills/ai-product-management && 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 "ai-product-management" agent skill from https://github.com/andreaskelm/pm-brain/tree/main/.claude/skills/ai-product-management into .gemini/skills/ai-product-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-product-management", 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 andreaskelm/pm-brain ai-product-managementInstalls 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 andreaskelm/pm-brain --skill ai-product-management -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/andreaskelm/pm-brain.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/ai-product-management .github/skills/ai-product-management && 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 "ai-product-management" agent skill from https://github.com/andreaskelm/pm-brain/tree/main/.claude/skills/ai-product-management into .github/skills/ai-product-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-product-management", 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 andreaskelm/pm-brain --skill ai-product-management -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install andreaskelm/pm-brain ai-product-management --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/andreaskelm/pm-brain.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/ai-product-management .opencode/skills/ai-product-management && 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 "ai-product-management" agent skill from https://github.com/andreaskelm/pm-brain/tree/main/.claude/skills/ai-product-management into .opencode/skills/ai-product-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-product-management", 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
ai-product-management- GitHub stars
- 234
- Token cost
- ~1.8k tokens
- SKILL.md length
- 968 words
- Files
- 3 (incl. references)
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs.
- Works in 5 steps: Preflight (always) → Pick the artifact → Draft outcome first → …
- The user says AI feature
- SKILL.md covers Is this AI, and is AI the…, Step 1 — Preflight (always), Step 2 — Pick the artifact and Step 3 — Draft outcome first, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
AI Product Management is an agent skill from andreaskelm/pm-brain. Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs. rules, prompt and context design, human-in-the-loop, safety guardrails, offline/online evals, golden sets, regression testing for AI, cost/latency budgets, and agent specs structured like PRDs (goals, tools, guardrails, success metrics). Use when the user says "AI feature", "add LLM", "build an agent", "copilot", "RAG", "prompt design", "eval our model", "hallucination", "AI product strategy", "chatbot…
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/ai-pm-guide.md` and `references/criteria.md`).
It sits in AI & LLM Engineering, covering LLM evaluation, PRD writing and LLM guardrails. The repository describes itself as: AI-powered product management thinking & operating system. Playbooks, guides, templates, and frameworks that bridge PM theory to daily execution.
When your agent uses it
- The user says AI feature
- AI product strategy
- To spec an agent
- Is deciding whether just add AI is real product work
Example prompts
- “AI feature”
- “add LLM”
- “build an agent”
- “/ai-product-management”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Preflight (always)
- Pick the artifact
- Draft outcome first
- Red flags as it takes shape
- Before calling it done
What it can do on your machine
Read from SKILL.md and the folder at commit 38696ac. 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.
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
AI Product Management loads about 1.8k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 164 tokens; SKILL.md has 968 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 968 words (~1,819 tokens).
“AI product work looks like normal PM until you ship — then quality is probabilistic, failures are weird, and "it works in the demo" is not a launch criterion. The failure mode I see most isn't picking the wrong model…”
- name
- ai-product-management
Files
SKILL.md and 2 other files (references) in .claude/skills/ai-product-management of andreaskelm/pm-brain.
- SKILL.md
- references/ai-pm-guide.md
- references/criteria.md
Open the folder on GitHubat commit 38696ac
Compare with similar skills
AI Product Management 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 |
|---|---|---|---|---|---|---|
| AI Product Management this skillandreaskelm/pm-brain | 234 | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Building Agent Systemstelagod/code-abyss | 244 | — | ~691 | Automated safety check: Pass | MIT | |
| Prompt Engineeringericrisco/rsc-harness | 180 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Chatbotericrisco/rsc-harness | 180 | — | ~3.3k | Automated safety check: Pass | MIT | |
| Prompt EngineerJeffallan/claude-skills | 12k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Controlww-w-ai/bkit-claude-code | 601 | — | ~1.6k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Prompt Engineering
ericrisco/rsc-harness
A skill your agent uses when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt…
Chatbot
ericrisco/rsc-harness
A skill your agent uses when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human…
Prompt Engineer
Jeffallan/claude-skills
Designs, tests and refines LLM prompts: zero-shot, few-shot and chain-of-thought patterns, system prompts, structured output schemas and evaluation test suites.
Control
ww-w-ai/bkit-claude-code
Control bkit automation level (L0-L4), view trust score, and manage guardrails.
Agent Spec
mohitagw15856/pm-claude-skills
Specify an autonomous or tool-using AI agent before building it.
More from andreaskelm/pm-brain
All 18 skills in this repoDiscovery Synthesis
andreaskelm/pm-brain
Plan customer discovery, turn interview snapshots into synthesis and evidence-based opportunities, build or update an Opportunity Solution Tree, map jobs and segments, and design RAT tests for the…
Eng Design Collab
andreaskelm/pm-brain
Partner effectively with engineering and design — feasibility and scope negotiation, tech debt tradeoffs, design reviews, discovery with builders, and PRD handoffs that don't get thrown away.
Experimentation
andreaskelm/pm-brain
Design and run product experiments at a practical PM level — A/B tests, hypothesis tests, rollouts, feature flags, and reading results without pretending to be a statistician.
Launch Gtm
andreaskelm/pm-brain
Plan, tighten, or review a product launch and go-to-market motion: rollout phases, beta and GA readiness, sales enablement, marketing launch, and release comms (internal and external).
North Star
andreaskelm/pm-brain
Define, sharpen, or audit a North Star metric and its input metrics tree, and decide which product metrics actually matter (leading vs.
Okr
andreaskelm/pm-brain
Write, draft, review, or fix OKRs (objectives and key results) for a team, product area, or quarter, and run weekly confidence check-ins, mid-cycle adjustments, and end-of-cycle grading.
Related
Questions about AI Product Management
What does AI Product Management do?
Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs. AI Product Management is an agent skill from andreaskelm/pm-brain. Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs.
When should I use AI Product Management?
AI Product Management fits situations like: the user says AI feature; AI product strategy; to spec an agent; is deciding whether just add AI is real product work.
How do I install AI Product Management in Claude Code?
Run `npx skills add andreaskelm/pm-brain --skill ai-product-management -a claude-code`. Or copy the skill folder (.claude/skills/ai-product-management in andreaskelm/pm-brain) into .claude/skills/ai-product-management in your project. Claude Code loads it when a task matches its description.
How do I install AI Product Management in Codex?
Run `npx skills add andreaskelm/pm-brain --skill ai-product-management -a codex`. Or copy the skill folder (.claude/skills/ai-product-management in andreaskelm/pm-brain) into .agents/skills/ai-product-management in your project. Codex loads it when a task matches its description.
Can I use AI Product Management 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 andreaskelm/pm-brain --skill ai-product-management -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-product-management, .gemini/skills/ai-product-management, .github/skills/ai-product-management and .opencode/skills/ai-product-management in your project.
What does AI Product Management need to run?
SKILL.md names no scripts, command-line tools or credentials: AI Product Management is instructions for the agent only.
Does AI Product Management 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 AI Product Management 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 AI Product Management use?
AI Product Management has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does AI Product Management use?
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.
What are the alternatives to AI Product Management?
Skills that share tags, products or a category with AI Product Management: Building Agent Systems (telagod/code-abyss, 244 stars), Prompt Engineering (ericrisco/rsc-harness, 180 stars), Chatbot (ericrisco/rsc-harness, 180 stars) and Prompt Engineer (Jeffallan/claude-skills, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AI Product Management?
andreaskelm (a GitHub user) maintains it in andreaskelm/pm-brain, which has 234 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 9, 2026.
Source: andreaskelm/pm-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.