Tooluck logoTooluck
SKILL.md

thinking-systems

Agent skill fromtjboudreaux/cc-thinking-skills

When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.

How to install thinking-systems

install thinking-systems
# install the cc-thinking-skills pack with the skills CLI
npx skills add tjboudreaux/cc-thinking-skills

# or add only this skill to Claude Code: copy the folder

skills/thinking-systems/

# into

~/.claude/skills/thinking-systems/ (all projects)

.claude/skills/thinking-systems/ (one project)

skills/thinking-systems/SKILL.md

MITFull file
1# Systems Mapping and Leverage
2
3Treat the problem as structure and interaction, not isolated parts. Map boundary, stocks/flows, loops/delays, and recurring patterns; intervene at the highest feasible leverage after a side-effect check.
4
5## When to Use
6
7- Symptom spans services/components; single-stack fixes fail or bounce.
8- A change in one place breaks another; behavior is emergent.
9- Problem recurs despite local fixes (structure, not only symptom).
10- Need to rank interventions when parameter/buffer tweaks do not stick.
11
12## When NOT to Use
13
14- Single-component linear bug with clear stack/diff—trace and fix.
15- Throughput limited by one obvious stage—use theory-of-constraints.
16- Decision is a consequence chain of one proposed action—use second-order.
17- Approach selection (plan vs probe vs stabilize)—use cynefin first.
18
19## Procedure
20
211. **Bound the system.** Name purpose, actors, boundary, and in/out flows. Exclude noise outside the decision horizon; include any path that can feed the symptom.
222. **Map stocks and flows.** List accumulating stocks (queue depth, debt, cache size, WIP) and the rates that fill/drain them. Note what changes slowly even when flows jump.
23…

Excerpt shown under the repository's MIT license.

More skills in cc-thinking-skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates