claude-skills is a large collection of reusable skills, commands, plugins, and supporting resources for coding agents across engineering, business, research, compliance, and productivity work. It is used by people who want agents such as Claude Code, Codex, Gemini CLI, or Cursor to follow specialized workflows. The catalogue contains selected skills and settings from the collection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alirezarezvani/claude-skills --skill postmortemgit clone --depth 1 https://github.com/alirezarezvani/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alirezarezvani/claude-skills/postmortem)<a href="https://agentmods.dev/skills/alirezarezvani/claude-skills/postmortem"><img src="https://agentmods.dev/badge/skills/alirezarezvani/claude-skills/postmortem/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alirezarezvani/claude-skills/postmortem"><img src="https://agentmods.dev/badge/skills/alirezarezvani/claude-skills/postmortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.01758 |
| Opus 5.5 | $0.00024 | $0.00703 |
| Sonnet 5.5 | $0.00012 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
postmortem scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/em:postmortem — Honest Analysis of What Went Wrong
Command: /em:postmortem <event>
Not blame. Understanding. The failed deal, the missed quarter, the feature that flopped, the hire that didn't work out. What actually happened, why, and what changes as a result.
Why Most Post-Mortems Fail
They become one of two things:
The blame session — someone gets scapegoated, defensive walls go up, actual causes don't get examined, and the same problem happens again in a different form.
The whitewash — "We learned a lot, we're going to do better, here are 12 vague action items." Nothing changes. Same problem, different quarter.
A real post-mortem is neither. It's a rigorous investigation into a system failure. Not "whose fault was it" but "what conditions made this outcome predictable in hindsight?"
The purpose: extract the maximum learning value from a failure so you can prevent recurrence and improve the system.
The Framework
Step 1: Define the Event Precisely
Before analysis: describe exactly what happened.
- What was the expected outcome?
- What was the actual outcome?
- When was the gap first visible?
- What was the impact (financial, operational, reputational)?
Precision matters. "We missed Q3 revenue" is not precise enough. "We closed $420K in new ARR vs $680K target — a $260K miss driven primarily by three deals that slipped to Q4 and one deal that was lost to a competitor" is precise.
Step 2: The 5 Whys — Done Properly
The goal: get from what happened (the symptom) to why it happened (the root cause).
Standard bad 5 Whys:
- Why did we miss revenue? Because deals slipped.
- Why did deals slip? Because the sales cycle was longer than expected.
- Why? Because the customer buying process is complex.
- Why? Because we're selling to enterprise.
- Why? That's just how enterprise sales works.
→ Conclusion: Nothing to do. It's just enterprise.
Real 5 Whys:
- Why did we miss revenue? Three deals slipped out of quarter.
- Why did those deals slip? None of them had identified a champion with budget authority.
- Why did we progress deals without a champion? Our qualification criteria didn't require it.
- Why didn't our qualification criteria require it? When we built the criteria 8 months ago, we were in SMB, not enterprise.
- Why haven't we updated qualification criteria as ICP shifted? No owner, no process for criteria review.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 194 lines · 60 tokens per session scan A ca1b7ab332c7
postmortem is a skill published in the GitHub repository alirezarezvani/claude-skills (28,607 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 1,758 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-24.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…