hjemmesidekongen/instinct-extractor
plugins/kronen/skills/instinct-extractor/SKILL.md
Extract atomic instincts from raw interaction observations. Reads .ai/instincts/observations.jsonl, identifies recurring patterns, and writes structured instincts to .ai/instincts/instincts.yml. Updates confidence scores and marks contradictions. Use when: reviewing accumulated observations, running the learning pipeline, updating instinct confidence, extracting patterns from recent session data, or seeding new instincts before instinct-evolve.
devops
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai instinct-extractorInstall 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: Apr 5, 2026, 5:14 PM51.3s2 files scanned
SKILL.md
- name:
- instinct-extractor
- description:
- >
- Use when:
- reviewing accumulated observations, running the learning
- user_invocable:
- false
- interactive:
- false
- depends_on:
- []
- type:
- data_validation
- - name:
- instincts_updated
- verify:
- At least one instinct created, updated, or decayed
- fail_action:
- Re-run pattern identification with lower threshold
- on_fail:
- Fix schema issues before writing output.
- on_pass:
- Report counts: new, updated, decayed, total active.
- model_tier:
- junior
- origin:
- kronen
- inspired_by:
- observation-recorder.sh + instincts-schema.yml
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- New skill for learning pipeline. Reads observations, outputs structured instincts.
instinct-extractor
Reads raw tool call observations and extracts recurring behavioral patterns as atomic instincts with confidence weights.
When to run
- After 50+ new observations have accumulated
- Before running instinct-evolve
- When a new domain of work has been active for several sessions
Steps
-
Load observations
- Read
.ai/instincts/observations.jsonl(last 200 lines) - Read existing
.ai/instincts/instincts.yml(to update vs. create) - Read schema:
plugins/kronen/resources/instincts-schema.yml
- Read
-
Identify patterns (see
references/process.mdfor methodology)- Group observations by
context_typeandsequence_key - Find sequences that appear 3+ times → candidate instincts
- Find error outcomes that follow the same sequence → contradiction candidates
- Group observations by
-
Update instincts.yml
- For each candidate: create new instinct or increment
evidence_count - For contradictions: increment
contradiction_count, apply confidence decay - Set
status: decayedfor instincts below 0.2 confidence
- For each candidate: create new instinct or increment
-
Output — Write updated
.ai/instincts/instincts.yml. Report: new, updated, decayed, total active.
Output: Instinct extraction complete. New: N | Updated: N | Decayed: N | Total active: N
Related Skills
hjemmesidekongen/brand-strategy
development
VerifiedTrustedCommunity
Creates a brand from scratch through market research and interactive sparring. Runs competitive research via Perplexity, then guides the user through positioning, audience, voice, values, and content pillars. Produces the full brand guideline set at .ai/brand/{name}/. Use when building a new brand, defining brand strategy for a product, or when /våbenskjold:create is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-loader
testing
VerifiedTrustedCommunity
Loads brand guidelines from .ai/brand/{name}/ and makes them available to the current context. Progressive disclosure: L1 confirms brand exists, L2 loads summary, L3 loads specific files on demand. Use when a downstream skill or user needs brand context, or when /våbenskjold:apply is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-evolve
documentation
VerifiedTrustedCommunity
Guided reinvention of an existing brand guideline. Loads current brand from .ai/brand/{name}/, identifies what to keep vs change, and walks the user through targeted evolution. Preserves brand equity while updating positioning, voice, or values. Use when refreshing a brand or when /våbenskjold:evolve is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-audit
development
VerifiedTrustedCommunity
Codifies an existing brand from materials, samples, and references. Analyzes provided content to extract voice patterns, values, and positioning. Produces the same guideline format as brand-strategy. Use when a brand already exists but isn't documented, or when /våbenskjold:audit is invoked.
SKILL.mdUpdated Apr 5, 2026