.pouch/skiff/skills.py

"""自研 skill 发现与解析。"""

from __future__ import annotations

import re
from pathlib import Path

from skiff.paths import SKILLS_DIR, TEMPLATE_DIR, ensure_skills_home
from skiff.registry import external_skill_path, load_registry


def list_owned_skills() -> list[str]:
    ensure_skills_home()
    if not SKILLS_DIR.is_dir():
        return []
    names: list[str] = []
    for entry in sorted(SKILLS_DIR.iterdir()):
        if not entry.is_dir():
            continue
        if entry.name.startswith("_"):
            continue
        if (entry / "SKILL.md").is_file():
            names.append(entry.name)
    return names


def owned_skill_path(name: str) -> Path:
    path = SKILLS_DIR / name
    if not (path / "SKILL.md").is_file():
        raise SystemExit(f"自研 skill 不存在: {name}")
    return path


def resolve_skill_source(name: str, *, source: str | None = None) -> tuple[Path, str]:
    """返回 (skill_path, kind)，kind 为 owned 或 external。"""
    ensure_skills_home()

    owned = SKILLS_DIR / name
    if source in (None, "owned") and (owned / "SKILL.md").is_file():
        return owned, "owned"

    registry = load_registry()
    if source in (None, "registry") and name in registry:
        path = external_skill_path(name, registry[name])
        if not (path / "SKILL.md").is_file():
            raise SystemExit(
                f"外部 skill {name!r} 尚未 fetch 或 path 中缺少 SKILL.md。"
                f"请运行: skiff fetch {name}"
            )
        return path, "external"

    if (owned / "SKILL.md").is_file():
        return owned, "owned"

    raise SystemExit(f"找不到 skill: {name}")


def read_skill_meta(skill_dir: Path) -> dict[str, str]:
    skill_md = skill_dir / "SKILL.md"
    if not skill_md.is_file():
        return {}
    text = skill_md.read_text(encoding="utf-8")
    if not text.startswith("---"):
        return {}
    end = text.find("\n---", 3)
    if end == -1:
        return {}
    frontmatter = text[3:end]
    meta: dict[str, str] = {}

    name_match = re.search(r"^name:\s*(.+)$", frontmatter, re.MULTILINE)
    if name_match:
        meta["name"] = name_match.group(1).strip().strip("\"'")

    desc_match = re.search(
        r"^description:\s*(?:>-|>\||>|-)?\s*\n((?:[ \t].+\n?)+)",
        frontmatter,
        re.MULTILINE,
    )
    if desc_match:
        lines = [line.strip() for line in desc_match.group(1).splitlines() if line.strip()]
        meta["description"] = " ".join(lines)
    else:
        inline = re.search(r"^description:\s*(.+)$", frontmatter, re.MULTILINE)
        if inline:
            meta["description"] = inline.group(1).strip().strip("\"'")

    return meta


def skill_description(name: str) -> str | None:
    meta = read_skill_meta(SKILLS_DIR / name)
    desc = meta.get("description")
    return desc.strip() if desc else None


def validate_skill_name(name: str) -> None:
    import re

    if not re.fullmatch(r"[a-z0-9]+(?:-[a-z0-9]+)*", name):
        raise SystemExit(
            f"skill 名称无效: {name!r}（小写 + 连字符，如 security-review）"
        )
    if name == "_template":
        raise SystemExit("不能使用保留名 _template")


_PLACEHOLDER_PATTERNS = (
    (r"^name:\s*skill-name\s*$", "skill-name"),
    (r"^#\s+Skill 名称\s*$", "Skill 名称"),
    (r"简要描述 skill 做什么、何时触发", "简要描述 skill 做什么"),
    (r"^-\s*触发场景 1\s*$", "触发场景 1"),
    (r"^\d+\.\s*第一步\s*$", "第一步"),
)


def validate_skill_dir(skill_dir: Path, expected_name: str) -> list[str]:
    """返回 skill 目录中的校验问题；空列表表示通过。"""
    issues: list[str] = []
    skill_md = skill_dir / "SKILL.md"
    if not skill_md.is_file():
        return ["缺少 SKILL.md"]

    text = skill_md.read_text(encoding="utf-8")
    if not text.strip():
        return ["SKILL.md 为空"]
    if not text.startswith("---\n"):
        return ["SKILL.md 缺少 YAML frontmatter"]

    end = text.find("\n---", 4)
    if end == -1:
        return ["SKILL.md frontmatter 未闭合"]
    frontmatter = text[4:end]
    keys = re.findall(r"^([A-Za-z0-9_-]+):", frontmatter, re.MULTILINE)
    unexpected = sorted(set(keys) - {"name", "description"})
    missing = sorted({"name", "description"} - set(keys))
    if missing:
        issues.append(f"frontmatter 缺少字段: {', '.join(missing)}")
    if unexpected:
        issues.append(f"frontmatter 只允许 name、description，发现: {', '.join(unexpected)}")

    meta = read_skill_meta(skill_dir)
    if meta.get("name") != expected_name:
        issues.append(
            f"目录名与 frontmatter name 不一致: {expected_name} != {meta.get('name', '(缺失)')}"
        )
    description = meta.get("description", "").strip()
    if not description:
        issues.append("description 不能为空")

    found_placeholders = [
        label
        for pattern, label in _PLACEHOLDER_PATTERNS
        if re.search(pattern, text, re.MULTILINE | re.IGNORECASE)
    ]
    if found_placeholders:
        issues.append(f"存在模板占位内容: {', '.join(found_placeholders)}")

    link_pattern = re.compile(r"!?\[[^\]]*\]\(([^)]+)\)")
    for target in link_pattern.findall(text):
        target = target.strip().split("#", 1)[0]
        if not target or "://" in target or target.startswith(("mailto:", "/")):
            continue
        if not (skill_dir / target).resolve().is_file():
            issues.append(f"引用文件不存在: {target}")

    for draft_file in ("brief.yaml",):
        if (skill_dir / draft_file).exists():
            issues.append(f"正式 skill 不应包含草稿文件: {draft_file}")
    return issues