- Home
- Skills
- Dmdorta1111
- Jac V1
- Problem Solving
problem-solving_skill
- Python
0
GitHub Stars
1
Bundled Files
3 weeks ago
Catalog Refreshed
2 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstart where the catalogue uses aiagentskills.
npx veilstart add skill dmdorta1111/jac-v1 --skill problem-solving- SKILL.md4.3 KB
Overview
This skill provides a compact toolkit of proven problem‑solving techniques for teams and individuals facing different types of stuckness. It maps common symptoms to focused methods—simplification cascades, collision‑zone thinking, meta‑pattern recognition, inversion exercises, and the scale game—so you can act quickly and deliberately. The intent is practical application: diagnose the blockage, run the appropriate technique, and iterate with recorded insights.
How this skill works
Start by matching the symptom you observe to one of the techniques. Each technique has a short process: expose the core assumption or pattern, run directed experiments (thought experiments, metaphors, scale tests), and record the resulting eliminations or new designs. Combine techniques when a single method doesn’t resolve the issue and document outcomes to reuse patterns across problems.
When to use it
- When implementations proliferate with many special cases (complexity spiraling)
- When conventional approaches don’t produce breakthroughs (innovation blocks)
- When similar problems recur across teams or domains (recurring patterns)
- When solutions feel forced by hidden assumptions (assumption constraints)
- When you’re unsure about production behavior or scale (scale uncertainty)
- When you’re generally stuck and need a dispatch to pick a technique
Best practices
- Diagnose first: match the symptom before applying a technique
- Run fast, low‑cost experiments to validate insights (thought experiments count)
- Document decisions and failed attempts to build a searchable pattern store
- Combine techniques deliberately rather than randomly for stronger results
- Test assumptions at extreme scales to reveal hidden failure modes
- Prefer eliminative insights: a single insight that removes multiple components
Example use cases
- A service with five ad‑hoc feature flags—use simplification cascades to find a unifying abstraction
- A product team hitting the same UX dead end—use collision‑zone thinking to import metaphors from another domain
- Multiple teams building similar adapters—apply meta‑pattern recognition to extract a reusable library
- A process everyone treats as immutable—run an inversion exercise to identify alternatives
- Unclear if a feature will survive production load—play the scale game to surface edge cases
FAQ
Start with the clearest symptom; if overlap persists, run a short two‑hour experiment with each top candidate and compare the insights produced.
How long should each technique take?
Aim for a timebox: 30–90 minutes for thought exercises or metaphor collisions, a day for pattern extraction, and up to a week for scale experiments depending on risk.