“destructive”的搜索结果

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

中文简介正在准备中。当前显示原文说明。

How NV oOS approval gates work for operator credentials and how to phrase tool requests so the human can adjudicate quickly. Use whenever a write-capable tool call pauses for approval or when planning a destructive change.

中文简介正在准备中。当前显示原文说明。

Reviews Laravel migrations for destructive operations, change() dropping modifiers, locking index creation on large tables (PostgreSQL), and asymmetric down().

中文简介正在准备中。当前显示原文说明。

Creates and reviews agent skills safely by enforcing deletion-prevention harness rules: no fixed absolute temp paths, no cwd-dependent cleanup, no wildcard deletes, no workspace-external file operations, no silent cleanup failures, and mandatory temp-root validation before any destructive command. Use when creating a new skill, updating an existing SKILL.md, or reviewing prompts/runbooks that include temp files, extraction, cleanup, PowerShell, bash, rm, del, Remove-Item, or archive expansion.

中文简介正在准备中。当前显示原文说明。

Show or explain the AOS go-gate mode (hard, soft, off) and the time-limited grants of this session. Use when the human runs /bdb-aos:gogate, asks why a git push, merge, publish or destructive command was blocked, or wants to know which grants are active. The agent only displays status and explains; only a plain `gogate ...` message typed by the human changes a mode or a grant.

中文简介正在准备中。当前显示原文说明。

Critical Git safety rules to prevent destructive operations. Use whenever performing git operations, reverting changes, or managing commits. Prevents accidental loss of work.

中文简介正在准备中。当前显示原文说明。

ALWAYS use this skill whenever you would otherwise ask the user a question in free-form chat -- for clarifications, confirmations (especially destructive actions), missing parameters, multiple-choice decisions, or structured form input. Elicitations are routed through the Unique AI Platform UI via `unique-cli elicit create` + `elicit wait` (the default polling pattern) or a single supervised `unique-cli elicit ask` call (only when your agent instructions say your environment supervises the wait) so the user gets a proper structured prompt and you get a structured answer back. Do NOT ask the user in plain chat when you can use this skill instead.

中文简介正在准备中。当前显示原文说明。

Natural, identity-preserving portrait retouching with a local CLI and a Busabase-backed review app. Use when the user asks to 美颜, 修人像, 磨皮, 提亮肤色, portrait retouch, headshot cleanup, profile-photo polish, before/after comparison, or batch portrait enhancement. Default to local non-destructive processing, preserve facial structure and skin texture, and require explicit approval before replacing or publishing any image.

中文简介正在准备中。当前显示原文说明。

Produce a single consolidated hardening report for the DSH node. Runs audit.sh, dome-check.sh, and machine-probe.py, parses their outputs, and writes one markdown file listing every passing check, every failure with a specific remediation command, and a top-line verdict (ALL GREEN / N ISSUES). Non-destructive — reads only, no auto-fix.

中文简介正在准备中。当前显示原文说明。

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

中文简介正在准备中。当前显示原文说明。

Automate detection, enrichment, and response playbooks for a SOC you operate. Keep humans in the loop for destructive actions.

中文简介正在准备中。当前显示原文说明。

Coordinate containment, eradication, and recovery for an authorized incident. Preserve evidence, communicate facts, and avoid destructive actions without approval.

中文简介正在准备中。当前显示原文说明。

Critical Git safety rules to prevent destructive operations. Use whenever performing git operations, reverting changes, or managing commits. Prevents accidental loss of work.

中文简介正在准备中。当前显示原文说明。

Deliver a small bounded change inside an initialized SDD Composy workspace through the quick path: at most five implementation files, a registered TASK, TDD, evidence, trace, and a verified verdict, escalating otherwise. Use for a precise objective with no existing task — 'ajuste rápido via SDD', 'quick fix under SDD', 'small change to X in the SDD flow'. Do NOT use for an already registered task (sdd-execute), for architecture, migrations, or destructive work, or in repositories without SDD Composy (other plugins' quick).

中文简介正在准备中。当前显示原文说明。

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)

中文简介正在准备中。当前显示原文说明。

Critical Git safety rules to prevent destructive operations. Use whenever performing git operations, reverting changes, or managing commits. Prevents accidental loss of work.

中文简介正在准备中。当前显示原文说明。

Backs up and restores OpenClaw workspace files before destructive operations such as sandbox rebuilds. Use when downloading workspace files from a sandbox, uploading restored files into a new sandbox, or preserving sandbox state across rebuilds. Trigger keywords - nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.

中文简介正在准备中。当前显示原文说明。

Set up Claude Code git safety guardrails that block dangerous git commands before execution. Use when the user asks to prevent git push, hard reset, git clean, destructive checkout/restore, or branch deletion from Claude Code hooks.

中文简介正在准备中。当前显示原文说明。

Run a non-destructive open-source, npm, or public release readiness checklist covering package metadata, provenance, license, internal artifact exposure, and dry-run evidence; complements security, shipping, and sanitizer reviews, and must not publish, delete, rewrite history, or mutate release state.

中文简介正在准备中。当前显示原文说明。

Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI namespace attacks through --extra-index-url resolution ordering, NuGet feed priority exploitation when multiple package sources are configured without clear directives, Maven and Gradle repository ordering where artifact resolution traverses repositories sequentially, Go module proxy abuse through GOPROXY misconfiguration, Ruby gems namespace squatting, and Docker image tag confusion with unqualified image references. Provides complete proof-of-concept methodology using safe callbacks including DNS canary via interactsh or Burp Collaborator and HTTP beacon with no destructive payload. Covers reconnaissance techniques for discovering internal package names through GitHub repository analysis, error ...

中文简介正在准备中。当前显示原文说明。