ysskrishna/ai-agent-skills / skills/first-principles-thinking
first-principles-thinking
VerifiedUse for first principles thinking, or when the user questions an inherited default: "why do we do it this way?", "is this cost really necessary?", "should we copy what competitors do?". Strips analogies and rebuilds from fundamentals. Skip for convention-following checklists.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.4 KB |
| references/example.md | markdown | 1.8 KB |
references/example.md
View on GitHub# Example: First Principles Thinking (light path)
Illustrative case. All details are invented.
**User:** "Every competitor offers a 99.99% uptime SLA, so we need one too, which means a multi-region setup. Is that actually necessary?"
**Reconstruction target:** the belief that we must offer 99.99% uptime and run multi-region.
**Pass:** Surface, Question, Bedrock, Rebuild, Implications.
**Surface**
- Convention: "competitors offer 99.99%, so customers expect it."
- Hidden comparison: our customers equal the competitors' customers.
**Question**
- **Assumption:** customers will not buy without 99.99%. **Why believed?** analogy to competitors. **What if false?** we avoid a costly architecture.
- **Assumption:** 99.99% requires multi-region. **Why believed?** common advice. **What if false?** one region with good failover may be enough.
**Bedrock**
- `[FUNDAMENTAL]` 99.99% allows about 52 minutes of downtime per year (arithmetic).
- `[FUNDAMENTAL]` Our contracts with two customers mention availability (user supplied).
- `[ASSUMPTION]` Other prospects need the same SLA.
- `[ASSUMPTION]` Our past outages would have been prevented by a second region.
**Rebuild**
1. Two known contracts set the actual requirement; read what level they state.
2. The cause of past outages decides whether a second region helps, so check the incident history.
3. Only if both point to multi-region is multi-region justified.
**Implications**
- So what: decide the SLA from contracts and outage causes, not from competitors' marketing pages.
- Cost of being wrong: if prospects do need 99.99% and we do not offer it, we lose some deals; if we over-build, we carry multi-region cost and complexity for little benefit.
- vs convention: convention starts from the architecture; this starts from the requirement.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |