القائمة
Seed OpenMemory with existing knowledge from key-prompts, decisions, tool learnings, and behavioral prefs. Safe to re-run — uses per-entry dedup.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | bootstrap-memory |
| description | Seed OpenMemory with existing knowledge from key-prompts, decisions, tool learnings, and behavioral prefs. Safe to re-run — uses per-entry dedup. |
| args | [] |
Incremental seeding of OpenMemory with project knowledge. Safe to re-run — checks each entry for duplicates before storing.
Setup auto memory symlinks. Run ~/.claude/scripts/setup-memory.sh. This creates the machine-specific projects/<encoded>/memory/ directories and symlinks them to the portable memory/*.md files. If the script fails, warn but continue — OpenMemory seeding doesn't depend on symlinks.
Health check. Call openmemory_list(user_id="global", limit=1). If unreachable, abort: "OpenMemory not reachable. Ensure Ollama is running (ollama serve) and the OpenMemory MCP server is registered."
Seed key prompt patterns. Read each file in ~/.claude/.claude/tracking/key-prompts/. For each ## entry:
simhash = md5(compressed_entry)[:16]openmemory_query(query=<full compressed entry text>, k=3, user_id="global") — for each result: compare the first 80 chars of content_preview against the entry (case-insensitive, whitespace-normalized); if they match, skip (count as skip_count). If no content match but a result has matching simhash in metadata, also skip.openmemory_store(content="<compressed entry>", tags=["prompt-pattern"], user_id="global", metadata={"sector": "procedural", "simhash": "<simhash>"})prompt_countShadow active decisions. Call pm_list_decisions(status="active"). For each decision:
simhash = md5(decision_summary)[:16]openmemory_query(query=<full decision summary text>, k=3, user_id="proj:dotclaude") — for each result: compare the first 80 chars of content_preview against the entry (case-insensitive, whitespace-normalized); if they match, skip (count as skip_count). If no content match but a result has matching simhash in metadata, also skip.openmemory_store(content="Decision [id]: <title> — <summary>", tags=["decision"], user_id="proj:dotclaude", metadata={"sector": "semantic", "decision_id": "<id>", "simhash": "<simhash>"})decision_countSeed tool learnings. Read ~/.claude/tool-learnings.md. For each - prefixed line (skip headers and blank lines):
- )simhash = md5(learning_text)[:16]openmemory_query(query=<learning_text>, k=3, user_id="global") — apply same dedup logic (first 80 chars content match OR simhash match → skip)openmemory_store(content="<learning_text>", tags=["tool-learning"], user_id="global", metadata={"sector": "procedural", "simhash": "<simhash>"})learning_countShadow behavioral prefs. Query correction_groups DB for promoted/manual entries:
sqlite3 ~/.claude/.claude/epics.db "SELECT text FROM correction_groups WHERE status IN ('promoted') OR source='manual' AND text != '' ORDER BY updated_at DESC;"simhash = md5(text)[:16]openmemory_query(query=<text>, k=3, user_id="proj:dotclaude") — apply same dedup logicopenmemory_store(content="<text>", tags=["behavioral-pref"], user_id="proj:dotclaude", metadata={"sector": "procedural", "simhash": "<simhash>"})pref_countReport. Print: "Bootstrapped N memories (P prompt patterns, D decisions, L tool learnings, B behavioral prefs). Skipped J duplicates."
Generate interactive HTML diagrams (flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, etc.) using Mermaid.js. Opens the result in the browser. Use when the user says "/diagram", "draw a flowchart", "make a diagram", "show me a flow", "sequence diagram", "class diagram", "state diagram", or any request for a visual diagram.
Graph-node skill: reads .ship-manifest.json (or story/epic IDs), launches one background agent per story to write plans/*.md files, applies critique checklist, updates DB with plan_file paths. Artifact-chain-aware version of /draft-plan. Consumes manifest from /plan-stories, produces plans/*.md for /env-preflight.
Spec-driven feature decomposition: accepts a FeatureSpec JSON (product, pattern, entity, fields, permissions, integrations, UI) and decomposes it into dependency-ordered stages using deterministic pattern DAGs. Creates stories via PM tools and writes .ship-manifest.json for downstream /draft-plans and /run-stories consumption. Use when the user says "/factory spec.json", "/factory --pattern crud-ui <inline JSON>", or "/factory --dry-run spec.json".
Merge a story worktree branch into its dev branch, push, clean up the worktree and branches, and mark the story done. Use when the user says "/merge-worktree", "/merge-worktree story-NNN", or "merge worktree".
Execute stories in parallel (where safe) using background agents, each working in an isolated git worktree branched from a shared dev branch. Handles dependency ordering, write-file conflict detection, and reports results. Use when the user says "/run-stories", "/run-stories story-NNN", "/run-stories epic-NNN", or any combination of story and epic IDs.
Bridge between presearch briefings (or inline args) and the /draft-plans skill. Parses inputs, dispatches the planner agent to create an epic and stories in the DB, and writes .ship-manifest.json for downstream consumption. Three invocation modes: briefing path, inline title+items, or resume an existing epic. Also handles execute mode for existing plan files (bypasses planner, creates DB entries directly). Use when the user says "/plan-stories presearch/topic.md", "/plan-stories \"Title\" 1. Feature 2. Feature", or "/plan-stories epic-NNN".