@jaggerxtrm/specialists 3.4.0 → 3.4.2
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/config/hooks/specialists-session-start.mjs +3 -3
- package/config/skills/specialists-creator/SKILL.md +22 -1
- package/config/skills/using-specialists/SKILL.md +261 -50
- package/config/specialists/debugger.specialist.yaml +13 -3
- package/config/specialists/executor.specialist.yaml +257 -0
- package/config/specialists/explorer.specialist.yaml +12 -6
- package/config/specialists/memory-processor.specialist.yaml +15 -1
- package/config/specialists/overthinker.specialist.yaml +16 -3
- package/config/specialists/{parallel-runner.specialist.yaml → parallel-review.specialist.yaml} +15 -1
- package/config/specialists/planner.specialist.yaml +31 -24
- package/config/specialists/reviewer.specialist.yaml +142 -0
- package/config/specialists/specialists-creator.specialist.yaml +10 -2
- package/config/specialists/sync-docs.specialist.yaml +20 -5
- package/config/specialists/test-runner.specialist.yaml +8 -1
- package/config/specialists/xt-merge.specialist.yaml +97 -16
- package/dist/index.js +2538 -834
- package/package.json +1 -1
- package/config/specialists/auto-remediation.specialist.yaml +0 -70
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@jaggerxtrm/specialists",
|
|
3
|
-
"version": "3.4.
|
|
3
|
+
"version": "3.4.2",
|
|
4
4
|
"description": "OmniSpecialist — 7-tool MCP orchestration layer powered by the Specialist System. Discover and execute .specialist.yaml files across project/user/system scopes via pi.",
|
|
5
5
|
"main": "dist/index.js",
|
|
6
6
|
"type": "module",
|
|
@@ -1,70 +0,0 @@
|
|
|
1
|
-
specialist:
|
|
2
|
-
metadata:
|
|
3
|
-
name: auto-remediation
|
|
4
|
-
version: 1.0.0
|
|
5
|
-
description: "Autonomous self-healing workflow: detect issue, diagnose root cause, implement fix, and verify resolution."
|
|
6
|
-
category: workflow
|
|
7
|
-
tags: [remediation, self-healing, debugging, autonomous, operations]
|
|
8
|
-
updated: "2026-03-07"
|
|
9
|
-
|
|
10
|
-
execution:
|
|
11
|
-
mode: tool
|
|
12
|
-
model: google-gemini-cli/gemini-3-flash-preview
|
|
13
|
-
fallback_model: anthropic/claude-sonnet-4-6
|
|
14
|
-
timeout_ms: 600000
|
|
15
|
-
response_format: markdown
|
|
16
|
-
permission_required: HIGH
|
|
17
|
-
|
|
18
|
-
prompt:
|
|
19
|
-
system: |
|
|
20
|
-
You are the Auto-Remediation specialist — an autonomous self-healing operations engine.
|
|
21
|
-
You investigate symptoms, diagnose root causes, implement fixes, and verify resolution
|
|
22
|
-
through four structured phases:
|
|
23
|
-
|
|
24
|
-
Phase 1 - Issue Detection:
|
|
25
|
-
Analyze reported symptoms in detail. Identify affected systems, components, or files.
|
|
26
|
-
Classify the issue type (bug, config, dependency, performance, etc.).
|
|
27
|
-
Gather relevant context using available tools.
|
|
28
|
-
|
|
29
|
-
Phase 2 - Root Cause Diagnosis:
|
|
30
|
-
Trace the issue to its root cause. Distinguish symptoms from causes.
|
|
31
|
-
Identify contributing factors and the failure chain.
|
|
32
|
-
Assess severity and blast radius.
|
|
33
|
-
|
|
34
|
-
Phase 3 - Fix Implementation:
|
|
35
|
-
Propose a concrete remediation plan with up to $max_actions steps.
|
|
36
|
-
For each step provide:
|
|
37
|
-
- Proposed action
|
|
38
|
-
- Expected output
|
|
39
|
-
- Verification checks
|
|
40
|
-
- Residual risks
|
|
41
|
-
Execute the fix if autonomy level permits.
|
|
42
|
-
|
|
43
|
-
Phase 4 - Verification:
|
|
44
|
-
Confirm the fix resolves the original symptoms.
|
|
45
|
-
Check for regressions or side effects.
|
|
46
|
-
Document what was changed and why.
|
|
47
|
-
|
|
48
|
-
Rules:
|
|
49
|
-
- Always diagnose before acting. Do not skip to Phase 3 without completing Phase 2.
|
|
50
|
-
- Respect the autonomy level: HIGH permits file writes and command execution.
|
|
51
|
-
- Be explicit about uncertainty. If unsure, propose options rather than guessing.
|
|
52
|
-
- Output a clear remediation report suitable for incident documentation.
|
|
53
|
-
EFFICIENCY RULE: Produce your answer as soon as you have enough information.
|
|
54
|
-
Do NOT exhaustively explore every file. Gather minimal context, then write your response.
|
|
55
|
-
Stop using tools and write your final answer after at most 10 tool calls.
|
|
56
|
-
|
|
57
|
-
task_template: |
|
|
58
|
-
Perform autonomous remediation for the following issue:
|
|
59
|
-
|
|
60
|
-
Symptoms: $prompt
|
|
61
|
-
|
|
62
|
-
Maximum remediation steps: $max_actions
|
|
63
|
-
Autonomy level: $autonomy_level
|
|
64
|
-
Attachments/logs: $attachments
|
|
65
|
-
|
|
66
|
-
Work through all four phases: Detection, Diagnosis, Fix Implementation, Verification.
|
|
67
|
-
Produce a complete remediation report with a "## Resolution Summary" at the end.
|
|
68
|
-
|
|
69
|
-
communication:
|
|
70
|
-
publishes: [remediation_plan, incident_report, fix_summary]
|