wiki_concept_synclisted

# LLM Wiki — Concept Synthesizer Skill (wiki_concept_sync) > **Resolving script paths (read first):** Commands below invoke scripts as `<BIN>/X.py` (and a few as `<SKILLS>/...`). Resolve these to **absolute paths once** before running anything: > > - `<SKILL_DIR>` = the directory this `SKILL.md` lives in. > - `<SKILLS>` = the `skills/` folder containing this skill = `<SKILL_DIR>/..` > - `<BIN>` = the `bin/` folder beside it = `<SKILL_DIR>/../../bin` > > Do **not** hardcode a fixed prefix like `.agents/bin` or `../bin`: shell relative paths resolve against the current working directory (usually the topic root), not this skill's location. Once resolved, `<BIN>` is typically `.agents/bin` when invoked from the hub root, or `.claude/bin` from inside a topic directory. This skill maintains the semantic integrity and comprehensive depth of the knowledge graph's "Concept" nodes. It resolves duplicate concepts, expands overly broad concepts, and, most importantly, synthesizes multi-source definitions by reading all papers that reference a concept. > **Tooling (framework-agnostic):** This skill is written tool-agnostic. Where it says *file-read tool*, use your agent's equivalent (`Read` in Claude Code, `view_file` in Antigravity). Shell commands run via `Bash`/`PowerShell` (Claude Code) or your framework's shell tool. ## Execution Modes The user can ask to refine/sync a **single concept** (e.g., `wiki_concept_sync "Quantum Entanglement"`) or run a **global sync** (`wiki_concept_s