Cynefin Agent Skill
Cynefin sense-making framework categorizing problems as Simple, Complicated, Complex, Chaotic, or Confused to select the right approach. Use when unsure how to tackle a problem.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/neurofoo/agent-skills --skill cynefinWhat comes with it
17 135 bytes besides the instructionThe instruction itself
14 sections, as written by the authorCynefin Analysis
Analyze a situation through the Cynefin framework to understand what type of problem it is and choose the appropriate response.
Instructions
Determine which Cynefin domain the problem belongs to, then apply the appropriate response approach. Be willing to recognize that parts of a problem may span multiple domains.
Output Format
Situation: [What we're analyzing]
Initial Assessment
Characteristics Check
| Characteristic | Yes/No/Maybe | Evidence |
|---------------|--------------|----------|
| Cause and effect are clear and predictable | | |
| Experts can analyze and determine the answer | | |
| Outcomes can only be understood in hindsight | | |
| The situation is unstable/in crisis | | |
| We genuinely don't know what kind of problem this is | | |
Domain Classification
Primary Domain: [Simple/Complicated/Complex/Chaotic/Confused]
Why this domain?
[Reasoning for the classification]
Domain-Appropriate Response
If SIMPLE/OBVIOUS
*Sense → Categorize → Respond*
Best Practice to Apply: [The established approach]
If COMPLICATED
*Sense → Analyze → Respond*
Experts Needed: [Who has the expertise?]
Analysis Required: [What to investigate?]
If COMPLEX
*Probe → Sense → Respond*
Safe-to-Fail Experiments:
| Probe | What We'd Learn | Amplify if... | Dampen if... |
|-------|-----------------|---------------|---------------|
| [experiment] | [insight] | [success indicators] | [failure indicators] |
Key Mindset: Don't try to predict. Try things, observe, adapt.
If CHAOTIC
*Act → Sense → Respond*
Immediate Stabilization: [What action do we take right now?]
If CONFUSED
*Break down, then categorize*
| Sub-problem | Likely Domain | Why |
|-------------|---------------|-----|
| [sub-problem] | [domain] | [reasoning] |
Boundary Warnings
| Transition | Warning Signs | What to Do |
|------------|--------------|------------|
| Simple → Chaotic | Complacency | Challenge assumptions |
| Complicated → Complex | Analysis not converging | Try probes instead |
| Complex → Chaotic | Loss of control | Stabilize fast |
Recommended Approach
Given this is a [DOMAIN] problem, we should:
- [Primary approach]
- [Supporting action]
Guidelines
- Most people default to Complicated (analysis) when Complex (probes) is needed
- "Best practice" is only valid in Simple domain
- In Complex, you can't predict—you can only experiment and adapt
- In Chaotic, act first, think later
$ARGUMENTS
Other skills for the same job
different authors, same section of the catalogue
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
How to use it
Take neurofoo/cynefin from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.