ysskrishna/ai-agent-skills / skills/systems-thinking
systems-thinking
VerifiedUse for systems thinking, or when a change may ripple beyond its target: "what are the side effects?", "why does this keep coming back?", "how do these teams or services affect each other?". Maps loops, delays and leverage points. Skip for single-step fixes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.5 KB |
| references/example.md | markdown | 1.8 KB |
references/example.md
View on GitHub# Example: Systems Thinking (light path)
Illustrative case. All details are invented.
**User:** "Our on-call engineers are burning out, so we added more alerts to catch problems earlier. Pages went up and so did the burnout. Why?"
**System in focus:** the alerting and on-call process of one engineering team.
**Pass:** Boundary, Structure, Dynamics, Delays, Leverage, Synthesis.
**Boundary**
- In: alerts, pages, on-call engineers, incident backlog. Out: product roadmap.
- Purpose: detect and fix customer-facing problems quickly without exhausting the team.
**Structure**
- Alerts -> Pages: each new alert rule adds pages.
- Pages -> Interrupted engineer time: lowers time for fixing causes.
- Unfixed causes -> Future alerts: the same problem fires again.
**Dynamics**
> **Loop [R]:** more alerts -> more pages -> less time to fix causes -> more repeat alerts - **Mechanism:** interruptions starve the work that would remove the alerts.
> **Loop [B]:** tired engineers -> slower response -> management adds alerts to catch problems "earlier" - **Mechanism:** the fix for slowness feeds loop R.
**Delays**
- Burnout shows up weeks after the alert load rises, so the cause looks unrelated.
**Leverage**
> **Leverage point:** a rule that every page must have an owner and a ticket to remove its cause - **Why it matters:** it changes the information flow so repeat alerts get fixed - **Risk of backfire:** teams delete alerts instead of fixing causes; review deleted alerts monthly.
**Synthesis**
1. Story: alerts were treated as a safety net, but each page took away the time needed to remove the causes, so pages kept growing.
2. Non-obvious: adding detection made the team slower at prevention.
3. Moves: pause new alert rules for one cycle; tag every page by cause; fund time to fix the top three repeat causes.
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 |