kiyoraka/mulahazah
Feature/Mulahazah-System/SKILL.md
MUST use when user says 'continuous-improvement', 'instinct status', 'what have you learned', 'show learned rules', 'mulahazah status', 'what patterns have you noticed', 'behavioral learning', 'show rules', or when user asks about session learning, accumulated rules, or patterns Claude has observed.
$ install --global
skillsauthnpx skillsauth add kiyoraka/project-ai-memorycore mulahazahInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 31, 2026, 6:45 AM218.5s5 files scanned
SKILL.md
- name:
- mulahazah
- description:
- MUST use when user says 'continuous-improvement', 'instinct status',
Mulahazah -- Behavioral Learning System
The AI that remembers how you work.
Activation
When this skill activates, output:
Mulahazah active -- reading learned rules for this project...
Then execute the protocol below.
Overview
Mulahazah is a passive observation layer built into your AI companion. It captures every tool call as structured data, analyzes patterns with Haiku, and writes actionable rules to rules.md. Those rules persist across sessions -- silently shaping how your AI works with you, without needing to be reminded each time.
Context Guard
| Context | Status |
|---------|--------|
| User asks about learned rules or patterns | ACTIVE -- full protocol |
| User types /continuous-improvement | ACTIVE -- full protocol |
| User says "what have you learned" | ACTIVE -- full protocol |
| User wants to see rule summary | ACTIVE -- full protocol |
| General coding conversation | DORMANT -- follow rules.md silently |
| User is explicitly asking about Forge skills | DORMANT -- use Forge skill instead |
Protocol
Step 1: Read Learned Rules
- [ ] Check
~/.claude/mulahazah/rules.md-- this is where learned rules live - [ ] If the file does not exist, report "No rules yet. Run
/continuous-improvementafter a work session to generate them." - [ ] Count and display total rules
Step 2: Session Reflection
Generate a reflection for this session:
## Reflection -- [Date]
- What worked:
- What failed:
- What I'd do differently:
- Rule to add:
If there is a "Rule to add", check ~/.claude/mulahazah/rules.md to see if it already exists. If not, append it.
Step 3: Analyze Observations (if requested or on /continuous-improvement)
- [ ] Check for
~/.claude/mulahazah/projects/*/observations.jsonl - [ ] If 5+ observations exist, run:
bash ~/.claude/mulahazah/bin/analyze.sh - [ ] Report what analysis found: new rules extracted, or "no new patterns yet"
- [ ] If no observations found, note that hooks may not be installed
Step 4: Report Observer Status
- [ ] Check if
~/.claude/mulahazah/observer.pidexists and process is alive - [ ] If running: show PID and confirm background analysis is active
- [ ] If not running: mention it is optional, show start command:
bash ~/.claude/mulahazah/agents/start-observer.sh
Step 5: Display Full Rule Status
Read ~/.claude/mulahazah/rules.md and display:
- Total rule count
- Rules grouped by date they were added
- Any rules that look outdated or contradictory (flag for user review)
Mandatory Rules
- Never hallucinate rules. Only report rules that exist in
~/.claude/mulahazah/rules.md. - Never invent observations -- only report what exists in observations.jsonl files.
- If
~/.claude/mulahazah/does not exist, output the installation prompt and stop. - Do not auto-apply rules without the user's awareness -- surface them in the reflection step.
- When rules.md exists and contains rules, follow them in your work during this session.
Edge Cases
| Situation | Behavior |
|-----------|----------|
| No rules.md yet | Report "No rules yet for this project. Run /continuous-improvement after your first work session." |
| Mulahazah not installed | Output: "Mulahazah is not installed. See Feature/Mulahazah-System/install-mulahazah.md to get started." |
| Observer not running | Note it is optional and show start command. Do not block skill execution. |
| analyze.sh not found | Report the missing path and remind user to re-run install steps. |
| Fewer than 5 observations | Note more tool calls are needed before patterns can be extracted. |
Synergy with Other Features
| Feature | How Mulahazah Interacts | |---------|-------------------------| | Forge | Rule clusters from rules.md with repeated patterns become Forge skill proposals. | | Save Diary | Active rules from rules.md are summarized in the session diary. | | Memory Consolidation | Triggers review of rules.md for stale or contradictory entries. | | Decision Log | Rules applied during a session are logged as behavioral decisions. |
Level History
- Lv.1 -- Base: rules.md persistence, session reflection, observation capture via
observe.sh, Haiku-powered analysis viaanalyze.sh,/continuous-improvementcommand. Background observer optional. (Origin: continuous-improvement v2.0, ported to MemoryCore as Mulahazah System. Tested end-to-end: observations captured, analyze.sh extracted "Grep → Read → Edit workflow" rule.)
Related Skills
kiyoraka/work-plan
development
VerifiedTrustedCommunity
MUST use when user says 'copy plan', 'append plan', 'resume plan', 'load plan', 'start the plan', 'continue the plan', 'execute plan', 'run the plan', 'pick up where we left off', or when the AI exits plan mode and needs to transfer the plan into execution format. This skill manages the full lifecycle of project plans — from plan output to tracked checkbox execution with per-todo commits.
347SKILL.mdUpdated May 31, 2026
kiyoraka/topic-diary
data-ai
VerifiedTrustedCommunity
MUST use when user says 'save topic', 'save to topic diary', 'remember this under', 'review topic', 'list topics', or when a generic 'save' request needs routing between session memory, daily diary, topic diary, or all targets.
347SKILL.mdUpdated May 31, 2026
kiyoraka/song-creation
documentation
VerifiedTrustedCommunity
Auto-triggers when user says 'create songs', 'new album', 'create album', 'make music', 'muse this', 'write a song', 'create a song', 'compose', 'song from image', 'album from image', 'generate album', 'write songs', or when user shares an image and wants to create music from it.
347SKILL.mdUpdated May 31, 2026
kiyoraka/Feature/Session-Briefing-System
tools
VerifiedTrustedCommunity
# 📋 Session Briefing — Skill Plugin ## Skill Name Session Briefing ## Trigger Words - Session start (automatic — fires before first response) - `"brief"` - `"session brief"` - `"what did we do last time"` - `"where did we leave off"` ## Suppress Trigger - `"skip brief"` — suppresses for this session only ## Activation Condition Fires automatically at the start of every new conversation session, before processing the user's first message. ## Behavior 1. Read `main/current-session.md` — extr
347SKILL.mdUpdated May 31, 2026