AI Product Management
andreaskelm/pm-brain
Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs.
Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real.
Install AI Agent Reliability
$ npx skills add mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills ai-agent-reliability --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-agent-reliability .claude/skills/ai-agent-reliability && 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-agent-reliability" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/ai-agent-reliability into .claude/skills/ai-agent-reliability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-reliability", 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/mohitagw15856/pm-claude-skills/tree/main/skills/ai-agent-reliabilityType 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 mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills ai-agent-reliability --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ai-agent-reliability .agents/skills/ai-agent-reliability && 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-agent-reliability" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/ai-agent-reliability into .agents/skills/ai-agent-reliability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-reliability", 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 mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills ai-agent-reliability --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ai-agent-reliability .cursor/skills/ai-agent-reliability && 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-agent-reliability" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/ai-agent-reliability into .cursor/skills/ai-agent-reliability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-reliability", 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/mohitagw15856/pm-claude-skills.git --path skills/ai-agent-reliability--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 mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills ai-agent-reliability --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ai-agent-reliability .gemini/skills/ai-agent-reliability && 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-agent-reliability" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/ai-agent-reliability into .gemini/skills/ai-agent-reliability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-reliability", 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 mohitagw15856/pm-claude-skills ai-agent-reliabilityInstalls 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 mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ai-agent-reliability .github/skills/ai-agent-reliability && 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-agent-reliability" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/ai-agent-reliability into .github/skills/ai-agent-reliability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-reliability", 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 mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills ai-agent-reliability --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ai-agent-reliability .opencode/skills/ai-agent-reliability && 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-agent-reliability" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/ai-agent-reliability into .opencode/skills/ai-agent-reliability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-reliability", 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-agent-reliability- GitHub stars
- 1.4k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 623 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real.
- Works in 6 steps: Enumerate the failure modes. Walk the… → Attach a check to each. Validation for… → Build real evals. A set of… → …
- Asked how do I test my AI agent
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: Map Failures, Catch… and Output Format, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
AI Agent Reliability is an agent skill from mohitagw15856/pm-claude-skills. Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. Use when asked how do I test my AI agent, make my automation reliable, my agent works sometimes, or how do I trust an AI workflow in production. Produces a map of where the agent can fail (bad input, hallucination, wrong tool call, edge cases, silent errors), the checks that catch each (validation, evals on real cases, human-in-the-loop gates, monitoring), a…
Its SKILL.md is about 1.3k 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, covering LLM evaluation and Human-in-the-loop approvals. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked how do I test my AI agent
- Make my automation reliable
- My agent works sometimes
- How do I trust an AI workflow in production
Example prompts
- “/ai-agent-reliability”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Enumerate the failure modes. Walk the agent's path — input, reasoning, tool calls, output, actions — and name where each step can break…
- Attach a check to each. Validation for input, verification for output, schema checks for tool calls, evals for quality, gates for…
- Build real evals. A set of representative and hard cases, scored — so you know it works and catch regressions before users do.
- Gate by consequence. Irreversible or external actions get a human check; low-stakes steps run free. Match the gate to the cost.
- Right-size it. Don't over-engineer a low-risk helper or under-test a system that moves money or data — effort follows stakes.
- Roll out to earn trust. Shadow mode, then low-stakes live, then expand — with monitoring and alerts — so reliability is proven, not assumed.
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. 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 Agent Reliability loads about 1.3k tokens when it runs. Until then it costs about 187 tokens; SKILL.md has 623 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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 623 words, ~1,260 tokens.
Download SKILL.mdSave it as
.claude/skills/ai-agent-reliability/SKILL.md (or your agent's skills folder).- name
- ai-agent-reliability
- description
- Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. Use when asked how do I test my AI agent, make my automation reliable, my agent works sometimes, or how do I trust an AI workflow in production. Produces a map of where the agent can fail (bad input, hallucination, wrong tool call, edge cases, silent errors), the checks that catch each (validation, evals on real cases, human-in-the-loop gates, monitoring), a right-sized reliability plan scaled to the stakes, and a rollout that earns trust incrementally — so an agent that works in a demo becomes one that works in reality. For builders putting AI agents into real workflows.
AI-Agent Reliability
An AI agent that works in a demo and one you can trust in production are different things — the gap is everything that happens when input is messy, the model hallucinates, a tool call goes wrong, or an error fails silently. This maps where your agent can fail and the specific checks that catch each, scaled to the stakes, plus a rollout that earns trust incrementally — so "works sometimes" becomes "works reliably."
What This Skill Produces
- A failure map — where this agent can go wrong: bad/unexpected input, hallucinated output, wrong or malformed tool calls, unhandled edge cases, silent failures, and runaway loops
- The catching checks per failure — input validation, output verification, evals on real cases, schema/format checks on tool calls, human-in-the-loop gates, and monitoring/alerts
- An eval approach — testing on a real set of cases (including the hard ones) so quality is measured, not assumed, and regressions are caught
- Human-in-the-loop placement — where a human must approve, scaled to consequence (irreversible/external actions gated, low-stakes automated)
- A right-sized plan — reliability effort matched to the stakes, not gold-plating a low-risk toy or under-testing a high-risk system
- A trust-building rollout — shadow mode → low-stakes → expand, with monitoring, rather than shipping it everywhere and hoping
Required Inputs
Ask for these if not provided:
- The agent — what it does, what tools/actions it takes, what it touches
- The stakes — what a failure costs (drives how hard to test and gate)
- Where it fails now — the flakiness you've seen (points at the weak spots)
- Your setup — the framework/tools, and whether you can add evals/monitoring
Framework: Map Failures, Catch Each, Earn Trust
- Enumerate the failure modes. Walk the agent's path — input, reasoning, tool calls, output, actions — and name where each step can break. You can't guard what you haven't named.
- Attach a check to each. Validation for input, verification for output, schema checks for tool calls, evals for quality, gates for consequential actions — a specific catch per failure.
- Build real evals. A set of representative and hard cases, scored — so you know it works and catch regressions before users do.
- Gate by consequence. Irreversible or external actions get a human check; low-stakes steps run free. Match the gate to the cost.
- Right-size it. Don't over-engineer a low-risk helper or under-test a system that moves money or data — effort follows stakes.
- Roll out to earn trust. Shadow mode, then low-stakes live, then expand — with monitoring and alerts — so reliability is proven, not assumed.
Show full SKILL.md (214 more words)Show less
Output Format
Agent reliability: [what it does] · stakes [level]
Failure map: [bad input · hallucination · wrong tool call · edge cases · silent errors · runaway loops]. Catch each: [failure → the check: validation / verification / schema / eval / human gate / monitor]. Evals: [the real + hard cases to test on, scored]. Human gates: [the consequential actions that need approval]. Right-sized: [effort matched to stakes — where to invest, where not]. Rollout: [shadow → low-stakes → expand, with monitoring].
Quality Checks
- Enumerates failure modes across the agent's whole path
- Attaches a specific check to each failure
- Includes evals on real and hard cases, scored
- Gates consequential actions with a human; automates low-stakes
- Scales effort to stakes; rolls out to build trust incrementally
Anti-Patterns
- Shipping a demo as if it's production-ready.
- No evals — quality assumed, regressions invisible.
- The same trust level for a summary and a money transfer.
- Gold-plating a toy or under-testing a high-stakes system.
- Big-bang launch with no shadow mode or monitoring.
Example Trigger Phrases
- "How do I test my AI agent so I can actually trust it?"
- "My automation works sometimes — how do I make it reliable?"
- "How do I put an AI workflow into production safely?"
- "What checks does my agent need before I let it run on real data?"
- "How do I know my agent won't do something dumb and irreversible?"
© mohitagw15856, 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/ai-agent-reliability of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
AI Agent Reliability 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 Agent Reliability this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.3k | Automated safety check: Pass | MIT | |
| AI Product Managementandreaskelm/pm-brain | 234 | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Loop Architectfabricioctelles/skills | 106 | — | ~2.1k | Automated safety check: Notes | MIT | |
| Looperksimback/looper | 710 | — | ~2.7k | Automated safety check: Notes | MIT | |
| Context Auditundefined-ui/second-brain-os | 1k | — | ~802 | Automated safety check: Pass | MIT | |
| Evalagentevals-dev/agentevals | 163 | — | ~904 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Loop Architect
fabricioctelles/skills
Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.
Looper
ksimback/looper
Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.
Context Audit
undefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail.
Eval
agentevals-dev/agentevals
Evaluate and score agent behavior against a golden reference.
Benchflow
benchflow-ai/benchflow
Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow.
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Related
Questions about AI Agent Reliability
What does AI Agent Reliability do?
Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. AI Agent Reliability is an agent skill from mohitagw15856/pm-claude-skills. Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real.
When should I use AI Agent Reliability?
AI Agent Reliability fits situations like: asked how do I test my AI agent; make my automation reliable; my agent works sometimes; how do I trust an AI workflow in production.
How do I install AI Agent Reliability in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a claude-code`. Or copy the skill folder (skills/ai-agent-reliability in mohitagw15856/pm-claude-skills) into .claude/skills/ai-agent-reliability in your project. Claude Code loads it when a task matches its description.
How do I install AI Agent Reliability in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a codex`. Or copy the skill folder (skills/ai-agent-reliability in mohitagw15856/pm-claude-skills) into .agents/skills/ai-agent-reliability in your project. Codex loads it when a task matches its description.
Can I use AI Agent Reliability 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 mohitagw15856/pm-claude-skills --skill ai-agent-reliability -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-agent-reliability, .gemini/skills/ai-agent-reliability, .github/skills/ai-agent-reliability and .opencode/skills/ai-agent-reliability in your project.
What does AI Agent Reliability need to run?
SKILL.md names no scripts, command-line tools or credentials: AI Agent Reliability is instructions for the agent only.
Does AI Agent Reliability 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 Agent Reliability 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 Agent Reliability use?
AI Agent Reliability 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 AI Agent Reliability use?
About 1.3k tokens (SKILL.md is roughly 5k 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 AI Agent Reliability?
Skills that share tags, products or a category with AI Agent Reliability: AI Product Management (andreaskelm/pm-brain, 234 stars), Loop Architect (fabricioctelles/skills, 106 stars), Looper (ksimback/looper, 710 stars) and Context Audit (undefined-ui/second-brain-os, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AI Agent Reliability?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.