一键导入
prime
Load behavioral patterns and recent reflections from Obsidian to prime the current session with cross-project self-knowledge
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Load behavioral patterns and recent reflections from Obsidian to prime the current session with cross-project self-knowledge
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Session-after-session product perfection loop. The strongest available model (Fable) directs — it walks the repo's context map context-by-context, proposes 5 challenged, high-value directions per context (features, design elevations, significant optimizations), gates them with the user until 10 are accepted, then orchestrates one Opus builder subagent per context in isolated worktrees while making every review/merge decision itself. All state lives in a linked Obsidian vault so any future session resumes the loop exactly where the last one stopped. Invoke with `/perfect [init|propose|build|status|reflect] [context-name]`.
Generate images with OpenAI gpt-image-2 (primary) or Leonardo AI (fallback), remove backgrounds, analyze with Gemini vision, and write SVG. For brand assets, UI illustrations, backgrounds, and icons.
Upgrade a generic UI icon or loading/empty state into a traced, motion-animated SVG. Generates flat trace-friendly art (via /leonardo tools), validates with Qwen vision, vectorizes to a clean multi-path SVG, and emits a Motion (framer-motion) reveal component. For icon + loading-state visual upgrades — NOT raw image generation (use /leonardo for that).
Hunts the highest-value surface of an LLM-powered app — the LLM call sites themselves — and drives them to their potential across three lenses. (1) Code quality of the AI plumbing (wrapping/chokepoint, logging/telemetry, caching/dedupe, schema+validation+self-repair). (2) Business value, by reusing the UAT Character method (representative users with jobs-to-be-done + a senior-quality bar + time-saved) but TESTING ONLY THE LLM PIECES — does each prompt's grounding and output clear the bar. (3) Model optimization as an alternative scenario — benchmark the same character inputs across models × thinking levels to find quality degradation/upgrade vs cost/latency. Everything is memorized in a linked **Obsidian vault** (one note per call site / character / model / session) so each scan builds on the last. Stack-agnostic engine; per-app specifics live in the repo's `tiger/` overlay (which IS the vault). Invoke with `/tiger init|scan|run|benchmark|recall|backlog [args]`.
Simulated User Acceptance Testing for the Personas desktop app, driven by Characters (representative users with jobs-to-be-done) rather than feature/code coverage. A capable LLM verifies each user journey in two chronological certification levels — L1 theoretical (over a code-derived surface model, cheap + mass-parallel) then L2 empirical (the LIVE app driven through the test-automation harness, serial) — judging through each Character's own consistent lens (time saved vs the manual way, and senior-in-role quality). Personas-specific: L1 reads context-map.json + the React/Rust source; L2 drives the running app via the test-automation server on :17320 (NOT a browser). Per-run specifics live in the repo's uat/ overlay. Invoke with `/uat init|update|run|promote [args]`.
Iteratively prototype a UI component through directional variants behind a tab switcher, then consolidate and refactor the winner. Use when the user wants to improve a component they consider a pillar of the app (visual appeal, creativity, UX clarity).
| name | prime |
| description | Load behavioral patterns and recent reflections from Obsidian to prime the current session with cross-project self-knowledge |
| allowed-tools | Read, Glob |
Load cross-project behavioral patterns from the shared Obsidian vault so this session benefits from accumulated self-knowledge. Run at the start of a conversation in any project.
Portable by design. Copy this skill to any repo's .claude/skills/prime/. It reads from a shared Obsidian vault, not from project-local files. The patterns it loads are about the user, not any specific codebase.
Skill family: /reflect analyzes recent sessions and writes Reflections/ (and promotes repeated signals into Patterns/) — this skill reads what /reflect writes. /reflect-me is the operator-profile sibling (Decision Mirror ledger → behavioral profile), a separate pipeline.
C:/Users/kazda/Documents/Obsidian/personasPatterns/ (promoted permanent rules — observed 3+ times)Reflections/ (periodic behavioral analysis from /reflect)This skill is best-effort. If the vault path doesn't exist (different machine, unsynced vault), or a folder is missing or empty, do NOT error or stop the conversation — proceed with whatever IS available and say plainly what was loaded and what wasn't (e.g. "vault not found at — running unprimed" or "2 patterns loaded; no reflections yet — run /reflect to create them"). One line per gap, then continue normally.
Glob C:/Users/kazda/Documents/Obsidian/personas/Patterns/*.md. Read each file.
These are permanent, validated behavioral rules — the highest-confidence signals about how the user works, promoted from reflections after appearing 3+ times. Pattern files are short; read them whole.
Glob C:/Users/kazda/Documents/Obsidian/personas/Reflections/*.md. Sort by filename (dates sort lexicographically). Read the 3 most recent (or however many exist).
Excerpt, don't dump. Pull out only the load-bearing lines — do not recite whole files into the conversation:
If no reflections exist, note it per Step 0 and continue with patterns alone.
Print a concise primer so the user sees what the session was primed on. Start with a 3–5 line digest, max 10 lines total:
Session primed — {N} patterns, {M} reflections (latest: {date}).
Patterns:
• {pattern — one line each}
Recent signals:
• {latest correction or emerging signal — one line each}
Current phase: {from most recent reflection}
Rules for the briefing:
After presenting the primer, absorb the loaded patterns as soft behavioral defaults for the rest of this session:
The patterns are defaults, not absolutes. If the user explicitly asks for something that contradicts a pattern, follow the user. Patterns capture past preferences; the current instruction always wins.