菜单
Always load when you need to write some skill.
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
| name | skill-writter |
| description | Always load when you need to write some skill. |
Naming: lowercase hyphens, 1-64 chars, matches folder
Frontmatter:
---
name: skill-name
description: What it does/ When to load
---
Tips:
: or other YAML-sensitive charactersskill(name="other-skill").pi/agent/skills/ — e.g., ~/.pi/agent/skills/skill-name/SKILL.mdThe description is the trigger - it tells the agent WHEN to use this skill.
Good triggers:
Bad triggers:
Rule: Write the trigger as "Use when..." in present tense. Specific enough to avoid false matches, general enough to catch all relevant cases.
Checklist:
After writing a skill, verify it loads correctly:
Use when opening a PR and driving it to green CI — push the branch, write a high-level PR description, watch checks, fix failures, and keep looping until green; also use when an already-open PR gets new commits.
Use when the user starts, resumes, switches, saves, or recalls a named task or ongoing work across sessions (e.g. "remember this", "continue X", "what was I doing on Y", "track this task").
Git commit workflow. Load when finishing any code-change task (after verification) to commit and push, or when explicitly staging/committing.
Use when modifying or adding a transform, loss, model, method, package, task-model, config, docs page, or example in a Lightly AG repo (lightly-ssl or lightly-train) and you need repo-specific conventions.
Spawn a subagent to run a task. Use when you want to delegate work to a separate pi instance.
Use when configuring or replicating LT-DETR v2 (ltdetrv2-s/m/l/x) COCO benchmarks via the lightly-train wrapper — model alias map, global vs per-rank batch size, recipe invariants, ECDet config mapping, cluster pins, and common gotchas.