Results for “snapshot”

分析 PyTorch memory snapshot pickle 文件（_dump_snapshot 导出的内存快照），提供内存峰值、碎片、泄漏、OOM 检测与交互式 HTML 报告。仅当用户明确提及 memory snapshot、内存快照、_dump_snapshot、pickle 内存文件 或需要对 snapshot pickle 做内存分析时才触发，不处理一般的 NPU 性能分析、SQLite 查询或通用内存问题。

The English summary is being prepared. Showing the original description.

Fix GraphSnapshot tests blocking CI on every feature PR. Use when: (1) every PR fails CI with "Snapshot mismatch" despite correct behavior, (2) fixing snapshots requires build → regen → commit → wait CI cycle per PR, (3) snapshot test in test/unit/*.test.js glob breaks on any intentional change, (4) pre-push hook runs pnpm build + snapshots:update on every push (2-3min overhead). Solution: move GraphSnapshot.test.js to test/unit/snapshots/ so it's excluded from the *.test.js glob. Run manually via pnpm snapshots:update when needed.

The English summary is being prepared. Showing the original description.

Publish a Mastra preview package from a pull request or branch. Check the exact commit, confirm publication, monitor the release workflow, and report verified npm tags with a ready-to-copy installation command.

• Publishing a preview package from a pull request
• Sharing a branch build under a custom npm tag
• Checking publication results and installation commands

Publish a Playground UI snapshot, a version for testing branch changes, through the npm release workflow. The skill checks publication results, updates the platform frontend's package versions and lockfile, and opens a pull request.

• Publishing a snapshot from the latest main
• Releasing current-branch Playground UI changes
• Opening a PR to update the platform frontend

Export/publish the live portfolio tracker as a static, stripped snapshot into the "Portfolio Snapshot" folder — an empty Trades section (first), the holdings table, and the 1-month-return bar chart baked to static SVG (scatter chart opt-in), with a Publish_Snapshot property. Strips all instruction/engine/log elements (refresh dataviewjs, tip callouts, Upcoming Earnings, Column Legend, Notes, Log). Use when the user says "snapshot the portfolio", "publish the portfolio", "export Live Portfolio", or "portfolio snapshot".

The English summary is being prepared. Showing the original description.

Refactors brittle snapshot tests into resilient, focused assertions. Provides strategies for reducing snapshot size, extracting meaningful assertions, and maintaining snapshots. Use for "snapshot testing", "snapshot refactoring", "brittle tests", or "assertion improvement".

The English summary is being prepared. Showing the original description.

Rehearse Convex schema changes on a deployment seeded with a production snapshot. Populate existing records, verify data and behavior, then repeat the proven sequence in production with explicit approval, keeping the snapshot available for rollback.

• Rehearse schema changes using a copy of production data
• Populate existing records before requiring a new field
• Verify migrated data and app behavior before production

Append a session/state snapshot to MEMORY.md (regardless of where it lives — for this repo it's `founder/MEMORY.md`). Use when the user says "snapshot memory", "save state to memory", "/memory-snapshot", "log what happened in MEMORY", or otherwise asks to record the current session's outcomes for the next orchestrator. Locates the project's MEMORY.md, prepends a dated entry above the previous snapshot (newest first), preserves every existing entry (NEVER overwrites or truncates), and reports back the file path + byte delta. Not for one-off feedback memories (use the user-level memory system at ~/.claude/.../memory/ for those). Not for trimming or deleting old entries.

The English summary is being prepared. Showing the original description.

Delete old snapshots from _Archive/Snapshots/. Accepts a day threshold (default 180). Also `daily-intel [days]` mode — prune auto-generated n8n scanning surfaces (news briefs, X dashboards) from Daily Intel/ older than 90 days. Use when user says "clean", "clean snapshots", "delete old snapshots", "clean daily intel", or when /lint flags stale snapshots.

The English summary is being prepared. Showing the original description.

Delete old snapshots from _Archive/Snapshots/. Accepts a day threshold (default 180). Also `daily-intel [days]` mode — prune auto-generated n8n scanning surfaces (news briefs, X dashboards) from Daily Intel/ older than 90 days. Use when user says "clean", "clean snapshots", "delete old snapshots", "clean daily intel", or when $lint flags stale snapshots.

The English summary is being prepared. Showing the original description.

Analyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked to find what retains objects, or investigating why objects survive GC. Provides snapshot parsing, comparison, retainer-path helpers, and scratchpad scripts.

The English summary is being prepared. Showing the original description.

Develop Rust filters for RTK through tests written before implementation. Use real command output as test inputs, check output snapshots and unexpected inputs, verify a minimum reduction target, and complete formatting, linting, and test checks before finishing.

• Adding a new RTK command filter
• Checking filtered output against saved snapshots
• Testing empty, malformed, or ANSI-colored input

The default code-driven browser path for interactive browsing work: drives any browser from code with token-efficient a11y snapshots (57% smaller via compactSnapshot), ref-based clicks, coordinate control (CUA), viewport pinning, CAPTCHA solving (reCAPTCHA, Turnstile, hCaptcha, slider, OCR), Chrome MV3 APIs (tabs/bookmarks/history/downloads/topSites), network snoop (read API JSON instead of DOM), flight-recorder trace (jsonl + HAR + screenshots), OOPIF-aware snapshots, dialog policy, human handoff for login/OTP, device emulation, request routes, stealth via CloakBrowser as the default owned engine with zero exposed CDP ports, and an attached engine that drives the user's own signed-in browser through BrowserSkill (connectBrowserSkill, bskSnapshot, one-click onboarding via bskOnboard). MUST USE for interactive browser work: scraping, blocked/WAF/JS-rendered pages, logins, the user's logged-in sites and open tabs, extension popups, form filling, screenshots, web QA, CAPTCHAs. The ulw-research browsing lane runs on ultimate-browsing, not this skill.

The English summary is being prepared. Showing the original description.

Investigate memory growth and out-of-memory failures in OpenClaw tests. Compare memory measurements and heap snapshots, records of objects held in memory, to distinguish cleanup leaks from retained test modules and verify targeted fixes.

• Investigating Vitest out-of-memory failures
• Comparing heap snapshots from the same process
• Distinguishing cleanup leaks from retained test modules

Create a reusable snapshot of an existing code repository, covering files, imports, components, and routes. It gives agents a shared reference for migration and editing work without repeatedly scanning the directory tree.

• Prepare repository structure for a code migration
• Record components and routes before making changes
• Reuse a repository snapshot across agent turns

Handle system backups and restore data from backup files while managing a SQLite database. The skill also covers data export, import, and incremental snapshots, which capture changes since an earlier saved state.

• Create a system backup
• Restore data from a backup file
• Export or import SQLite data

Compare two saved cost-summary JSON snapshots to identify changes in total spending, sessions, and model costs. Set limits on spending increases or token growth to flag cost regressions during pull request checks.

• Comparing spending before and after a pull request
• Finding models responsible for cost changes
• Failing checks when spending exceeds set limits

Guide Git operations with explicit authorization for history changes and destructive actions. It defines recovery snapshots before discarding work, careful handling of locks and index corruption, and checks that keep unexplained changes out of commits.

• Keeping completed changes available for review before committing
• Saving a recovery snapshot before an authorized discard
• Handling Git locks or a corrupted index

Manage files and storage buckets in Tigris through its official CLI. Agents can upload and download objects, generate temporary sharing URLs, take snapshots, and manage access keys and permissions with structured JSON output.

• Upload, download, and copy files in Tigris
• Create temporary upload or download links
• Take a bucket snapshot before making changes

Inspect CPU, memory, disk, and accelerator information alongside container and scheduler limits. Produce a JSON snapshot with identifying details removed and conservative worker and memory estimates for planning local workloads, without running stress tests.

• Choosing worker counts before a large local job
• Checking CPU and memory limits inside a container
• Comparing resource snapshots before and after changes

Helps implement centralized settings management in Java with Azure App Configuration. Covers environment-specific settings, feature flags that control feature availability, and snapshots that preserve settings at a particular point in time.

• Manage settings separately for development and production
• Configure feature flags for gradual rollouts
• Preserve release settings in snapshots

Analyze large logs, test results, API responses, and files outside the conversation, then return focused findings. It guides agents to save, process, index, and search outputs while limiting how much raw data enters their working context.

• Extracting errors from large logs
• Summarizing test failures and build warnings
• Inspecting JSON and CSV data

Bring cash, sales, deals, upcoming commitments, and urgent messages into a one-page business brief for small business owners. Use connected tools or owner-supplied figures to show changes, specific risks, and today's most important action.

• Checking business performance in a daily brief
• Reviewing weekly results and unresolved issues
• Identifying overdue invoices and stalled deals

Investigate growing memory usage in Qwen Code CLI by comparing heap snapshots, records of objects in memory. Trace what keeps objects alive, identify likely causes, and repeat the workload to verify a fix.

• Investigating steadily growing memory usage
• Tracing references that keep objects alive
• Finding growing arrays, caches, or event listeners