Install
$ agentstack add skill-proophboard-skills-navigation ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Prooph Board — Navigation
This skill defines how to interpret and generate deeplinks for prooph board.
You are responsible for:
- extracting identifiers from deeplinks
- retrieving chapter data via MCP tools
- focusing responses on a specific element or slice
- generating deeplinks for user navigation
This skill is read-only and focus-oriented.
Core Principle
Deeplinks Are References, Not Resources
A deeplink is a pointer to a location, not something to open.
DO NOT:
- fetch the URL
- open the URL
- interpret it as content
DO:
- extract identifiers
- retrieve data via MCP
- focus your response accordingly
Deeplink Structure
https://flow.prooph-board.com/link/{workspaceId}/{chapterId}/{type}/{targetId}
Where:
workspaceId→ workspace identifierchapterId→ chapter identifiertype→elementorslicetargetId→ elementId or sliceId
Behavior 1 — Resolving Deeplinks
Use this when the user provides a deeplink.
Step 1 — Parse the Deeplink
Extract:
- workspaceId
- chapterId
- type
- targetId
Step 2 — Retrieve Chapter Data
Use MCP tool:
get_chapter_details(workspaceId, chapterId)
Step 3 — Locate Target
Based on type:
element
- find element by
elementIdin chapter data
slice
- find slice by
sliceIdin chapter data
Step 4 — Focus the Response
Once located:
- treat the element/slice as the primary context
- apply user instructions ONLY to that target
- ignore unrelated parts unless explicitly requested
Focus Rules
When a deeplink is used:
- the response MUST be scoped to the referenced element or slice
- do NOT analyze the entire chapter unless asked
- do NOT generalize beyond the target
Error Handling
Target Not Found
If the element/slice cannot be found:
- state that it was not found in the chapter
- ask the user for clarification or a correct link
Invalid Deeplink
If structure is invalid or incomplete:
- explain what is missing
- ask for a valid deeplink
Missing Type
If type is missing:
- do NOT guess
- ask the user whether it refers to an element or slice
Behavior 2 — Generating Deeplinks
Use this when:
- referencing specific elements or slices
- summarizing work
- asking targeted questions
- guiding user navigation
Deeplink Format
Always generate links in this format:
https://flow.prooph-board.com/link/{workspaceId}/{chapterId}/{type}/{targetId}
When to Generate Deeplinks
Create deeplinks when:
- pointing to specific modeling issues
- referencing elements in feedback
- asking questions about a specific element/slice
- summarizing important parts of a model
Example Usage
Instead of:
> The "Place Order" command looks incorrect.
Write:
> The command “Place Order” may violate modeling rules: > https://flow.prooph-board.com/link/{workspaceId}/{chapterId}/element/{elementId}
Precision Rules
- always use exact IDs from data
- NEVER invent IDs
- NEVER approximate or truncate IDs
Anti-Patterns
Fetching Deeplinks
Incorrect:
- treating the URL as a data source
Losing Focus
Incorrect:
- analyzing unrelated elements when a deeplink is provided
Guessing Targets
Incorrect:
- assuming element/slice when not specified
- inventing IDs
Integration with Other Skills
After resolving a deeplink:
- use Event Modeling skills for modeling or critique
- remain scoped to the referenced element/slice
Goal
Correct behavior means:
- precise parsing of deeplinks
- deterministic data retrieval via MCP
- strict focus on referenced element or slice
- clear, navigable deeplink generation for the user
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: proophboard
- Source: proophboard/skills
- License: MIT
- Homepage: https://skills.prooph-board.com/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.