leegitw logo

leegitw skills on Remote OpenClaw

9 skills published by leegitw. Each listing includes a one-command install for Claude Code, OpenClaw, Codex, and Hermes, plus a link to the upstream source.

neon-soul

Reads AI agent memory files, identifies recurring patterns, and generates a SOUL.md identity document with full provenance tracking. Patterns appearing 3 or more times are promoted to axioms. Synthesis runs locally via Ollama with no questionnaires or manual input.

Coding Agents & IDEs1.5K installs

pattern-finder

Compares two text sources to find shared principles — ideas that appear in both, even when expressed differently. Uses an N-count system where N=2 means two independent sources agree on the same idea. Shows what's shared, what's unique to each source, and flags divergence types.

Apple Apps & Services1.3K installs

consciousness-soul-identity

Reads memory files from your local workspace, finds recurring patterns across conversations, and writes a SOUL.md identity document where every claim traces back to a source file. Synthesis is incremental — only new or changed memory gets processed. Runs entirely on your machine via a local Ollama instance.

Coding Agents & IDEs865 installs

failure-memory

Detects failures during agent sessions, records them as observations with recurrence, confirmation, and disconfirmation counters, and promotes patterns to constraints when evidence thresholds are met. All data stays in a local `.learnings/` directory with no external API calls.

Notes & PKM577 installs

context-verifier

context-verifier computes SHA-256 hashes of files and checks them before agent operations. It detects when a file has changed between when it was read and when an edit is about to happen. Context packets bundle file metadata and checksums into JSON records stored locally for audit or comparison.

Coding Agents & IDEs543 installs

visual-concept

Converts technical conversations and insights into visual concept guides for music videos or visual content. Produces symbolic imagery, color palette arcs, and thematic direction. Does not generate images or prescribe shot lists.

Coding Agents & IDEs472 installs

safety-checks

Runtime safety verification suite that consolidates model version pinning, fallback chain validation, cache staleness detection, and cross-session state checks. All operations are local file and metadata reads with no external API calls or data transmission. Consolidates four separate skills into a single aliased command.

AI & LLMs459 installs

side-quests

Takes a technical insight or conversation context and generates three creative artifacts: a Suno-ready song, a visual concept guide, and a full TED talk. Works from current conversation context by default or a user-supplied topic. All logic runs inline with no external API calls.

Coding Agents & IDEs248 installs

ted-talk

Converts technical conversations and insights into structured 40-50 minute TED-style presentations. Output follows a fixed arc: hook, problem setup, core concept, real-world examples, broader implications, closing, and Q&A preparation. Works from current conversation context or an explicit topic argument.

AI & LLMs235 installs