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 ysskrishna/ai-agent-skills --skill analytical-thinkinggit clone --depth 1 https://github.com/ysskrishna/ai-agent-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/ysskrishna/ai-agent-skills/analytical-thinking)<a href="https://agentmods.dev/skills/ysskrishna/ai-agent-skills/analytical-thinking"><img src="https://agentmods.dev/badge/skills/ysskrishna/ai-agent-skills/analytical-thinking/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/ysskrishna/ai-agent-skills/analytical-thinking"><img src="https://agentmods.dev/badge/skills/ysskrishna/ai-agent-skills/analytical-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00110 | $0.00759 |
| Opus 5 | $0.00055 | $0.00380 |
| Sonnet 5 | $0.00022 | $0.00152 |
| Haiku 4.5 | $0.00011 | $0.00076 |
Grade A, and why
analytical-thinking 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 10d ago.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytical Thinking
Clarity beats cleverness. End with answers tied to structure and stated confidence.
How to run it with this skill: one clearly headed section per step in this order: Frame → Decompose → Hypotheses → Evidence → Synthesis. Insert Options matrix only when Setup calls for it (after Evidence, before Synthesis).
Setup (run before starting)
In one short block:
- Analytical question — precise, ideally falsifiable
- Default pass — Frame → Decompose → Hypotheses → Evidence → Synthesis (state this line)
If data availability or definitions are missing, ask at most 3 questions in one message, then proceed. Note any remaining gaps or working guesses in plain language (no bracket tags in Setup).
If the user is choosing among concrete alternatives, after Evidence insert Options matrix: rows = options, columns = criteria (state weights if any), qualitative scores (− / 0 / +) with one-line justification per cell — then finish with Synthesis.
The Steps
Frame
Question type (estimate, compare, explain, predict, optimize). Unit of analysis and baseline (even if hypothetical).
Decompose
Tree or table: factors, drivers, or workstreams. Each child node should be MECE-ish (mutually exclusive where it matters; collectively exhaustive enough for the decision).
Hypotheses
Ranked H1, H2, H3 — what would we expect to observe if each were true? What would falsify each?
Evidence
For each hypothesis: Observation: … — Strength note: one short sentence on how much this observation supports or undermines the hypothesis and the main limit (no Strong/Moderate/Weak labels). Caveat: …
If no real data, run a thought experiment section instead — label bullets [THEORETICAL].
Synthesis
- Answer — direct response to the analytical question
- Key uncertainty — what single unknown swings the answer most
- Next data / step — what to collect or run next
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.
- 10d ago First seen · 83 lines · 110 tokens per session scan A 9b88043f1d75
analytical-thinking is a skill published in the GitHub repository ysskrishna/ai-agent-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 759 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
dev-tools-skills-guide
Guide for development and code tools skills including document processing, browser automation, testing frameworks, and IDE integrations.
marketing-skills-guide
Guide for marketing and growth skills including SEO, copywriting, CRO, email campaigns, paid ads, and product launch strategies.
ai-llm-skills-guide
Guide for AI Agents and LLM development skills including RAG, multi-agent systems, prompt engineering, memory systems, and context engineering.
awesome-skills-overview
Guide for understanding and contributing to the awesome-skills curated resource list. Use this skill when adding resources, organizing categories, or maintaining README.md consistency (no duplicates).
agent-platforms
Guide for multi-platform skill compatibility across Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and other AI coding agents.
security-skills-guide
Guide for security-related Agent Skills including penetration testing, code auditing, threat hunting, and forensics skills.