Align user-facing documentation with v5.5.1 codebase state (#99)

* Initial plan

* Update documentation to reflect v5.5.1 state and mem-search skill

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>

* Update hooks documentation to clarify 6 hooks + pre-hook architecture

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>

* Complete documentation alignment with mem-search skill naming

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>

* Fix remaining old skill path references in troubleshooting docs

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>

* Documentation alignment complete - all tests pass

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>

* Fix hallucinated /skill command references - skills are auto-invoked

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
This commit is contained in:
Copilot
2025-11-12 14:59:04 -05:00
committed by GitHub
parent 1c9da73d5f
commit 7bdf6dbfe1
13 changed files with 207 additions and 133 deletions
+4 -4
View File
@@ -160,9 +160,9 @@ Context injection uses progressive disclosure for efficient token usage:
- Shows full summary details **only if** generated after last observation
- Token cost: ~50-200 tokens for index view
### Layer 2: On-Demand Details (Skill-Based Search)
### Layer 2: On-Demand Details (mem-search Skill)
- Ask naturally: "What bugs did we fix?" or "How did we implement X?"
- Claude auto-invokes search skill to fetch full details
- Claude auto-invokes mem-search skill to fetch full details
- Search by concept, file, type, or keyword
- Timeline context around specific observations
- Token cost: ~100-500 tokens per observation fetched
@@ -195,7 +195,7 @@ The `/clear` command clears the conversation context visible to Claude AND re-in
## Searching Your History (v5.4.0+)
Claude-Mem now uses skill-based search for querying your project history. Simply ask naturally:
Claude-Mem uses the mem-search skill for querying your project history. Simply ask naturally:
```
"What bugs did we fix last session?"
@@ -204,7 +204,7 @@ Claude-Mem now uses skill-based search for querying your project history. Simply
"Show me recent work on this project"
```
Claude automatically recognizes your intent and invokes the search skill, which uses HTTP API endpoints to query your memory efficiently.
Claude automatically recognizes your intent and invokes the mem-search skill, which uses HTTP API endpoints to query your memory efficiently.
**Token Savings**: ~2,250 tokens per session start vs previous MCP approach