john/prompts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sten 6 implementation

Browse Source
This commit is contained in:
John Lancaster
2026-06-20 14:31:24 -05:00
parent 3885774e5b
commit 467e1d3c35
7 changed files with 119 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/usage.md
+25 -7
View File
@@ -72,7 +72,7 @@ In this project, "automatic loading" should be read as a preference you express
In practice, there are two reliable ways to make skill content available in chat:
1. explicit resource attachment through `Add Context > MCP Resources` or `MCP: Browse Resources`
2. MCP tool invocation such as `search_patterns` followed by `get_skill_document_by_id`
2. MCP tool invocation using `list_resources`/`read_resource` (ResourcesAsTools), with thin catalog tools as parity fallback
Instruction quality and metadata quality still matter, because they influence whether Copilot recognizes that the MCP server is relevant and chooses the tool path well.
@@ -146,6 +146,21 @@ Weak metadata reduces Copilot match quality and increases wrong context injectio
If you skip the catalog/index step, behavior is less predictable and may either miss relevant skills or pull too much context.
## Optional Tool Search Mode
When tool catalogs grow, FastMCP search transforms can reduce tool-list noise for tool-only clients.
Runtime switches:
1. `PERSONAL_MCP_TOOL_SEARCH=none|regex|bm25` (default `none`)
2. `PERSONAL_MCP_TOOL_SEARCH_MAX_RESULTS=<positive int>` (default `5`)
Behavior:
1. `regex` uses deterministic regex matching for targeted queries.
2. `bm25` uses ranked natural-language matching.
3. `list_resources` and `read_resource` stay visible so resource-backed fallback remains primary.
## Copilot Instruction Pattern
If you want Copilot to use `personal-mcp` skill content more reliably, the instruction file should describe three things clearly:
@@ -170,7 +185,7 @@ When a task may match a documented implementation pattern from `personal-mcp`:
1. Start with catalog-first discovery.
2. Prefer MCP resources when the chat surface exposes resource attachment.
3. If MCP resource attachment is unavailable, use catalog tools instead.
3. If MCP resource attachment is unavailable, use `list_resources`/`read_resource` first, then thin catalog tools if needed.
4. Load only the most relevant skill document, or at most 2 skill documents.
5. Reconcile loaded skill guidance with the actual repository code before making changes.
@@ -183,9 +198,11 @@ Preferred resource order:
Preferred tool fallback order:
1. `search_patterns`
2. `get_pattern_by_id`
3. `get_skill_document_by_id`
1. `list_resources`
2. `read_resource`
3. `search_patterns`
4. `get_pattern_by_id`
5. `get_skill_document_by_id`
If confidence is low after discovery, ask one clarifying question before loading more context.
```
@@ -225,8 +242,9 @@ Suggested instruction policy text:
1. Start with catalog-first discovery.
2. Prefer MCP resources when the chat surface exposes resource attachment.
3. Otherwise use catalog tools to search and load one or two likely skill documents.
4. If confidence is low, ask one clarifying question before loading more.
3. Otherwise use tool fallback to load one or two likely skill documents.
4. Prefer `list_resources`/`read_resource` first when operating in tool-only clients.
5. If confidence is low, ask one clarifying question before loading more.
## Summary