mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command `/mykg`. The user describes intent in natural language (extract, append, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right `mykg` CLI command from the live `--help` output, confirms, runs it, and drives the inbox/outbox watch loop for LLM-bearing commands (extract-graph). For read-only queries, prefers MCP tools when the mykg MCP server is online, falling back to reading session files directly, with the `mykg query` CLI as a last-resort fallback. Ensures `.mcp.json`
npx skills add SenolIsci/mykg --skill mykg --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# mykg — single slash command, intent-driven CLI dispatcher This skill is the agent-mode driver for **mykg**. The user types `/mykg <free text>` describing what they want; the skill parses the intent, assembles the matching `mykg` CLI command (with live `--help` as ground truth for flags), confirms expensive actions, and executes. For LLM-bearing subcommands (`extract-graph`), it then drives the inbox/outbox watch loop. For synchronous subcommands (`walkthrough`, `approve-schema`, `parse-docs`), it shells out and reports. For the read-only `query` verb, it prefers MCP tools when the mykg MCP server is online, falling back to reading session files directly when MCP is unavailable, with the `mykg query` CLI as a last-resort fallback. The pipeline code, the orchestrator, all prompts, all 12 pipeline steps, and the inbox/outbox contract are **unchanged**. This skill only changes how `mykg` is invoked from inside Claude Code. --- ## Read before answering — discipline rule Before answering any domain question about the corpus this project's mykg sessions cover, **read the latest session's graph files first**. Your training data is not grounded in this project's source documents; the grap
- Read before answering — discipline rule
- Default behaviour — fresh session unless told otherwise
- When to invoke — intent examples
- Discovering CLI flags
- MCP configuration — ensure .mcp.json exists
- Stage 1 — parse intent
- --append-with-grow-schema — expanding the schema incrementally (D52)
- --freeze-schema — bring-your-own-schema extraction
- fetch-web flags and special cases
- Special --from-step values for the orphan-connect step
- Stage 2 — confirm intent before running
- Stage 3 — verify agent mode is active
- Stage 4 — execute
- Stage 4a — LLM-bearing path (extract-graph)
mykg extract-graph ./docs --base-schema ontology.ttl --freeze-schema Resolve active profile (top-of-file `profile:` line). Read schema_max_restarts inside the active profile block. if [ "$CURRENT" = "0" ]; then fi python3 - <<PYEOF if [ ! -f mykg_config.yaml ]; then echo "No mykg_config.yaml found in $(pwd)." echo "Run \`mykg init --profile agent-claude-code\` from a shell first, then re-invoke /mykg." exit 1
What does the mykg skill do?
Run mykg knowledge-graph commands inside Claude Code from one slash command `/mykg`. The user describes intent in natural language (extract, append, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right `mykg` CLI command from the live `--help` output, confirms, runs it, and drives the inbox/outbox watch loop for LLM-bearing commands (extract-graph). For read-only queries, prefers MCP tools when the mykg MCP server is online, falling back to reading session files directly, with the `mykg query` CLI as a last-resort fallback. Ensures `.mcp.json`
How do I install it?
Run `npx skills add SenolIsci/mykg --skill mykg --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From SenolIsci/mykg, a repository with 63 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.