clawdi 0.5.7 → 0.5.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/index.js +88 -84
- package/dist/skills/clawdi/SKILL.md +31 -2
- package/package.json +1 -1
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: clawdi
|
|
3
|
-
description: "Cross-agent long-term memory for the current user: their preferences, coding habits, named projects / repos / tools, past bugs and architecture decisions,
|
|
3
|
+
description: "Cross-agent long-term memory + session history for the current user: their preferences, coding habits, named projects / repos / tools, past bugs and architecture decisions, AND their past agent conversations across Claude Code / Codex / OpenClaw / Hermes. Surface this skill BEFORE answering any question about the user themselves, their work, or their history — even when phrased abstractly (e.g. 'what do I usually use for X', 'find the session where I worked on auth'). Also provides connected-service tools (Gmail, GitHub, Notion, Drive, Calendar, etc.) and reads Clawdi share URLs (https://cloud.clawdi.ai/s/...) the user pastes."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# Clawdi Cloud
|
|
7
7
|
|
|
8
|
-
You have access to Clawdi Cloud tools via the `clawdi` MCP server. Use them aggressively — memory retrieval is the highest-leverage
|
|
8
|
+
You have access to Clawdi Cloud tools via the `clawdi` MCP server. Use them aggressively — memory + session retrieval is the highest-leverage capability you have here.
|
|
9
9
|
|
|
10
10
|
## Memory
|
|
11
11
|
|
|
@@ -46,6 +46,35 @@ Write memories as standalone sentences with full context — include names, not
|
|
|
46
46
|
|
|
47
47
|
Do NOT save trivial facts that are obvious from the code itself, or generic programming knowledge.
|
|
48
48
|
|
|
49
|
+
## Sessions
|
|
50
|
+
|
|
51
|
+
Two tools for reading and finding past agent conversations stored in Clawdi Cloud:
|
|
52
|
+
|
|
53
|
+
- `session_read` — Fetch a single session by reference and return its full conversation as Markdown. Accepts a Clawdi share URL (`https://cloud.clawdi.ai/s/{uuid}`) OR a session UUID for one of the user's own sessions. Handles owned and shared sessions transparently — you don't need to know which one.
|
|
54
|
+
- `session_search` — Find sessions in the user's history by keyword. Trigram-ranked substring search with typo tolerance. Returns matching sessions with summary, project, timestamps, and **session UUIDs you can pass back to `session_read`**.
|
|
55
|
+
|
|
56
|
+
### When to read — call `session_read` whenever the user references a specific session
|
|
57
|
+
|
|
58
|
+
MUST call when the user's message includes:
|
|
59
|
+
- A Clawdi share URL (e.g. `https://cloud.clawdi.ai/s/11111111-2222-3333-4444-555555555555`) — pass the full URL
|
|
60
|
+
- A direct reference like "open the session where I did X" or "the one from yesterday about auth" — first call `session_search` to find the UUID, then `session_read` to load it
|
|
61
|
+
|
|
62
|
+
Do NOT call WebFetch on `cloud.clawdi.ai/s/...` URLs — `session_read` is the right tool and avoids the WebFetch permission prompt.
|
|
63
|
+
|
|
64
|
+
### When to search — bias toward calling, similar to `memory_search`
|
|
65
|
+
|
|
66
|
+
MUST call `session_search` when:
|
|
67
|
+
- The user asks about prior work: "what did I do about the focus bug", "find the session where I migrated auth", "show me last week's debugging session"
|
|
68
|
+
- They reference a past investigation by topic but don't name a specific session
|
|
69
|
+
- They want to continue / reuse approach from a prior conversation
|
|
70
|
+
|
|
71
|
+
### Difference from `memory_search`
|
|
72
|
+
|
|
73
|
+
- `memory_search` finds **stored facts / preferences / decisions** the user (or a previous agent run) explicitly extracted. Short rows; high signal.
|
|
74
|
+
- `session_search` finds **full conversations** in the corpus. Long rows; useful when the user wants the original context, not just the takeaway.
|
|
75
|
+
|
|
76
|
+
When the user's request is **conceptual** ("how do I usually do X"), prefer `memory_search`. When they want to **revisit a specific past conversation** ("the session where..."), use `session_search`. When unsure, try `memory_search` first (cheaper, faster), fall back to `session_search` if empty.
|
|
77
|
+
|
|
49
78
|
## Connectors
|
|
50
79
|
|
|
51
80
|
Connected service tools (Gmail, GitHub, Notion, etc.) are dynamically registered from the user's Clawdi Cloud dashboard. They appear as individual tools like `gmail_fetch_emails`, `github_list_issues`, etc.
|