Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert C4 Context-level documentation specialist. Creates high-level system context diagrams, documents personas, user journeys, system features, and external dependencies.
.claude/skills/c4-context/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | — | — |
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-06 | ✗→✓ | ▲ Improved | — | — |
resources/implementation-playbook.md.One-sentence description of what the system does]
Detailed description of the system's purpose, capabilities, and the problems it solves]
...
...
Mermaid diagram showing system, users, and external systems]
## Context Diagram Template
According to the [C4 model](https://c4model.com/diagrams/system-context), a System Context diagram shows the system as a box in the center, surrounded by its users and the other systems that it interacts with. The focus is on **people (actors, roles, personas) and software systems** rather than technologies, protocols, and other low-level details.
Use proper Mermaid C4 syntax:
C4Context title System Context Diagram
Person(user, "User", "Uses the system to accomplish their goals") System(system, "System Name", "Provides features X, Y, and Z") System_Ext(external1, "External System 1", "Provides service A") System_Ext(external2, "External System 2", "Provides service B") SystemDb(externalDb, "External Database", "Stores data")
Rel(user, system, "Uses") Rel(system, external1, "Uses", "API") Rel(system, external2, "Sends events to") Rel(system, externalDb, "Reads from and writes to")
**Key Principles** (from [c4model.com](https://c4model.com/diagrams/system-context)):
- Focus on **people and software systems**, not technologies
- Show the **system boundary** clearly
- Include all **users** (human and programmatic)
- Include all **external systems** the system interacts with
- Keep it **stakeholder-friendly** - understandable by non-technical audiences
- Avoid showing technologies, protocols, or low-level details
## Example Interactions
- "Create C4 Context-level documentation for the system"
- "Identify all personas and create user journey maps for key features"
- "Document external systems and create a system context diagram"
- "Analyze system documentation and create comprehensive context documentation"
- "Map user journeys for all key features including programmatic users"
## Key Distinctions
- **vs C4-Container agent**: Provides high-level system view; Container agent focuses on deployment architecture
- **vs C4-Component agent**: Focuses on system context; Component agent focuses on logical component structure
- **vs C4-Code agent**: Provides stakeholder-friendly overview; Code agent provides technical code details
## Output Examples
When creating context documentation, provide:
- Clear system descriptions (short and long)
- Comprehensive persona documentation (human and programmatic)
- Complete feature lists with descriptions
- Detailed user journey maps for all key features
- Complete external system and dependency documentation
- Mermaid context diagram showing system, users, and external systems
- Links to container and component documentation
- Stakeholder-friendly documentation understandable by non-technical audiences
- Consistent documentation format
## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-24 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +46 percentage points is the difference between those two pass rates over the 24 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.