kiyoraka/log-decision
Feature/Decision-Log-System/SKILL.md
Auto-triggers when a non-obvious decision is made during conversation. Also triggers on 'log decision', 'why did we choose', 'what was the trade-off', 'should we use A or B' (after resolution), or when user asks about past reasoning behind a choice.
$ install --global
skillsauthnpx skillsauth add kiyoraka/project-ai-memorycore log-decisionInstall 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, 6:46 AM240.9s3 files scanned
SKILL.md
- name:
- log-decision
- description:
- Auto-triggers when a non-obvious decision is made during conversation.
Log Decision -- Append-Only Decision Tracking Skill
Every important "why" captured, every trade-off remembered.
Activation
When this skill activates, silently read main/decisions.md.
- If user is logging a decision: capture and confirm
- If user is searching past decisions: find and present
- If a decision-worthy moment is detected: offer to log it
Context Guard
| Context | Status | |---------|--------| | User says "log decision" | ACTIVE -- capture decision | | User says "why did we choose [X]?" | ACTIVE -- search decision log | | Non-obvious decision made in conversation | ACTIVE -- offer to log | | User says "should we use A or B?" (after resolved) | ACTIVE -- log the choice | | Session end with unlogged decisions | ACTIVE -- prompt to log | | Mid-conversation (no decision context) | DORMANT |
Protocol
On Decision Detection
- [ ] Identify the decision: what was chosen and what was rejected
- [ ] Determine if it's non-obvious (skip trivial/obvious choices)
- [ ] If non-obvious: offer to log it or log automatically if user said "log decision"
On Logging a Decision
- [ ] Get current date (YYYY-MM-DD)
- [ ] Write a short descriptive title
- [ ] Compose entry in format:
## YYYY-MM-DD -- Short title **Context**: What situation prompted this decision **Decision**: What was chosen (and what was rejected) **Rationale**: Why -- trade-offs, constraints, evidence - [ ] APPEND to
main/decisions.md(after the last entry) - [ ] Confirm: "Logged decision: [title]"
On Searching Decisions
- [ ] Read
main/decisions.md - [ ] Search for keywords matching the user's query
- [ ] Present matching decision(s) with full context
- [ ] If no match: inform user and offer to log a new entry
On Reversing a Decision
- [ ] DO NOT edit the original entry
- [ ] APPEND a new entry referencing the original:
## YYYY-MM-DD -- Reversed: [original title] **Context**: Why the original decision is being reconsidered **Decision**: New choice, referencing the old one **Rationale**: What changed -- new information, constraints, or priorities
Mandatory Rules
- Append-only -- NEVER edit or delete past entries
- Context + Decision + Rationale -- all three fields required for every entry
- Include rejected alternatives -- document what was NOT chosen and why
- Non-obvious only -- skip trivial choices (using git, formatting preferences)
- Natural detection -- detect decision-worthy moments without requiring explicit commands
Edge Cases
| Situation | Behavior | |-----------|----------| | No decisions.md file | Create it with template from install protocol | | No matching decision found | Inform user, offer to log a new entry | | Vague decision ("we went with the better one") | Ask user to clarify alternatives and reasoning | | Multiple related decisions | Log each as a separate entry with cross-references | | Reversal of past decision | Append new entry with "Reversed:" prefix, never edit original |
Level History
- Lv.1 -- Base: decision detection, append-only logging, Context+Decision+Rationale format, search, reversal tracking.
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