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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/majiayu000/claude-skill-registry --skill scope命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据,按主题分组汇总"我都做了什么",并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
基于 SOC 职业分类
正在显示 SKILL.md
| name | scope |
| description | Hard-block edits outside declared frozen directories via PreToolUse hook. |
| practices | ["ddd-bounded-context","design-by-contract","mythical-man-month"] |
| hexagonal_role | driven-adapter |
| consumes | [] |
| produces | ["filesystem-gate"] |
| context_rel | [{"kind":"supplier-to","with":"domain"}] |
| skill_api_version | 1 |
| context | {"window":"isolated","intent":{"mode":"none"},"sections":{"exclude":["HISTORY","INTEL","TASK"]},"intel_scope":"none"} |
| metadata | {"tier":"meta","dependencies":[]} |
| output_contract | stdout: scope status / lock state; stderr: blocked-edit reason from hook |
Purpose: Declare which directories are in scope for the current work session. Edits outside the declared scope are hard-blocked by a PreToolUse hook.
YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.
/scope freeze cli/cmd/ao/ # Freeze a single directory
/scope freeze cli/cmd/ao/ skills/scope/ # Freeze multiple (additive)
/scope unfreeze cli/cmd/ao/ # Remove one frozen directory
/scope unfreeze # Clear ALL frozen directories
/scope status # Show current lock state
/scope status --json # JSON output
When .agents/scope.lock declares one or more frozen_dirs:
Edit, Write, or Bash tool call whose target path is outside every frozen directory is rejected by hooks/edit-scope-guard.sh with a structured stderr reason and a non-zero exit code (Claude Code converts that into a tool-use refusal).frozen_dirs is empty, the hook short-circuits with exit 0 (no enforcement; allow everything).The lock file is written via cli/internal/llmwiki/scope_guard.go:SafeAtomicWrite, so concurrent freeze / unfreeze calls converge atomically (last writer wins, never tears).
/scope freeze <dir>...Append one or more directories to the frozen set. Idempotent; re-freezing an already-frozen directory is a no-op. Updates acquired_at (ISO-8601) and acquired_by (session id or PID) on every write.
/scope unfreeze [<dir>]Without arguments, clears the entire frozen set. With one or more directory arguments, removes just those entries. Removing a directory that is not frozen is a no-op.
/scope status [--json]Print the current lock state. With --json, emit a single JSON object matching the schema in references/lock-file-format.md. Without flags, print a human-readable summary including each frozen directory, the acquisition timestamp, and the acquiring session.
/scope guard (future combo skill)Reserved for a follow-up skill that combines freeze + status + spawn-orchestration. Not implemented in this release; documented here for forward reference.
.agents/scope.lock is a single JSON object. Full schema lives in references/lock-file-format.md. Key fields:
schema_version — currently 1frozen_dirs — list of repo-relative directory prefixes (trailing slash optional)acquired_at — ISO-8601 UTC timestampacquired_by — string identifying the writer (session id, PID, or label)User says: /scope freeze cli/cmd/ao/ cli/internal/scope/
What happens:
ao scope freeze cli/cmd/ao/ cli/internal/scope/ writes .agents/scope.lock via SafeAtomicWrite.hooks/edit-scope-guard.sh (registered as PreToolUse on Edit|Write|Bash) consults the lock on every subsequent tool call.Write to skills/foo/SKILL.md is rejected; a worker editing cli/cmd/ao/scope.go proceeds.User says: /scope unfreeze
What happens:
ao scope unfreeze rewrites .agents/scope.lock with frozen_dirs: []..agents/scope.lock path. Wave 2 (issue I5) migrates the path through lib/ao-paths.sh.agentopsd (cron-cadence) compose; this skill is purely session-boundary.rm -rf, git reset --hard, DROP DATABASE, kubectl delete, terraform destroy) — including allowlist layering, one-shot override codes, and PreToolUse wiring — see references/destructive-command-guard-patterns.md. Wire it alongside the scope guard when a wave touches infrastructure or shared data./hooks-authoring.