← All creators

layersistem

Organization

Persistent memory + consolidation layer for Claude Code (and other agent CLIs). Local, plain-markdown, no API key.

5 indexed · 0 Featured · 0 stars · avg score 73
Prolific

Categories

Indexed Skills (5)

AI & Automation Listed

humanizer

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.

0 Updated today
layersistem
AI & Automation Listed

brain-consolidate

Nightly consolidation for the brain vault (the waking equivalent of sleep consolidation). Use when asked to "consolidate", "distil today's decisions", "scan for superseded notes", at the end of a session or before a compaction. Collects a window of decision records, finds their older neighbours, and produces a five-part PROPOSAL report. The agent never applies anything - the human approves.

0 Updated today
layersistem
AI & Automation Listed

caveman

Mandatory base skill, every session. Two surfaces. CHAT: ultra-compressed caveman (about 75% fewer tokens, full technical accuracy; levels lite/full/ultra). DELIVERABLE: text a third human reads (mail, doc, report, wiki, release note, UI copy, issue body) written as natural full-sentence prose with AI-writing tells removed (humanizer folded in). Trigger: /caveman, "caveman mode", "be brief", "less tokens", or any deliverable writing. Merged 1 Sep 2026 (Burak): humanizer absorbed, wenyan levels dropped. Original kept in ~/.claude/skills-archive/.

0 Updated today
layersistem
Code & Development Listed

five-gates

Working discipline for serious multi-step work: five sequential gates (scope, evidence, self-attack, verify, calibrate) plus an authority map, a smell list and a few anti-patterns. Load it proactively for debugging, installs, reviews, migrations, measurements - any task where being confidently wrong is expensive. Also load it when someone says "focus up", "be disciplined", "slow down and do this properly".

0 Updated today
layersistem
AI & Automation Listed

find-skills

Discover agent skills for a task and install them ONLY with explicit human (Burak) approval. Use when user asks "is there a skill for X", "find a skill", "skill var mı", "install skill", or when a task would clearly benefit from a missing skill. Discovery free; install gated. Never auto-installs.

0 Updated today
layersistem

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.