Results for “disk”

Run a task iteratively over a user-specified duration by dispatching subagents. The orchestrator stays strictly linear and time-checked, but each iteration fans out MULTIPLE subagents in parallel over independent units (and those subagents may fan out further). Shared state — a compact progress digest and a growing environment cheatsheet — lives on disk and is passed to every subagent BY REFERENCE, killing the per-subagent rediscovery tax. Every subagent first reads an initialiser preamble that points it at that shared state and makes it write findings back, so the cheatsheet populates itself; role prompts are produced ONCE on the filesystem by a single scaffold command and dispatched by path, never re-typed per dispatch. Subagents persist their results to disk and return only a tiny status, so the orchestrator's context stays small and lasts. The orchestrator classifies the goal as FINITE or OPEN-ENDED: finite lists may finish early; open-ended goals use the full duration, never idle, never manufacture busywork. Use when the user gives a task and a duration and wants it ground out iteratively by subagents over that time.

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

Inspect reviewed Grafana infrastructure evidence for host or fleet CPU usage, memory load, disk space, and system load. Use for server-health checks, capacity symptoms, resource saturation, disk pressure, cloud or local host comparisons, and bounded infrastructure triage.

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

Systematic VPS cleanup — analyze files, categorize by importance, safely delete temporary/old data to free disk space

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

Validate Commodore 1540/1541/1541C/1541-II compatible disk-drive behavior in EMULATORS, including IEC serial bus protocol, device numbers, KERNAL traps, CBM DOS commands/status, D64 image parsing, BAM/directory/file chains, PETSCII filenames, 6502 drive CPU/ROM/RAM expectations, 6522 VIA wiring, GCR/track/sector geometry, motor/head timing, and compatibility boundaries for 1541-like devices. Use when Codex reviews or edits C64, VIC-20, C264, COMMODORE disk, serial I/O, D64, CBM DOS, IEC, VIA, GCR, or 1541 drive code.

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

Expert en forensique numérique (disk imaging, memory analysis, network forensics, chain of custody)

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

Digital forensics v3 — disk imaging, memory analysis, network forensics, chain of custody, legal

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

Expert en forensique numérique avancée (disk imaging, memory analysis, network forensics, reporting, chain of custody, incident response)

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

Fetch a URL and save the body to a temp file so you can pipe it through rg / jq / awk instead of dumping the whole page into the conversation. Use this whenever a user gives you a URL to read - articles, docs, PRs, gists, README files, blog posts, anything HTTP. Returns a path on disk; the agent then greps the path for the relevant section and quotes only what matters. Strongly preferred over the built-in webfetch tool when (a) the page is more than a few KB, (b) the user wants to find a specific phrase / table / code block on the page, (c) you need to keep the long page out of context, or (d) you want to inspect raw HTML alongside rendered markdown. Triggers: 'fetch', 'fetch this URL', 'fetch and save', 'fetch the page', 'pull this', 'grab this article', 'read this URL', 'read the docs at', 'mirror this page', 'page is too long', 'save the page so I can grep it', 'put it on disk so I can rg', 'cache this URL'.

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

集群数据管理 Skill —— 涵盖数据使用规范、压缩优化、数据共享（ACL）、文件扫描与清理、文件完整性校验、genozip 基因组压缩等全流程。Use when the user asks about: managing data on the HPC cluster, compressing genomic files (fq/bam/vcf), sharing data between users/groups, scanning for large files or cleaning up disk space, checking file integrity (md5/gzip/bam), using genozip, checking disk quota, or any data lifecycle management task on the NCPGR HPC cluster.

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

集群数据管理 Skill —— 涵盖数据使用规范、压缩优化、数据共享（ACL）、文件扫描与清理、文件完整性校验、genozip 基因组压缩等全流程。Use when the user asks about: managing data on the HPC cluster, compressing genomic files (fq/bam/vcf), sharing data between users/groups, scanning for large files or cleaning up disk space, checking file integrity (md5/gzip/bam), using genozip, checking disk quota, or any data lifecycle management task on the NCPGR HPC cluster.

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

Runs Docker Desktop and its WSL2 layer, checking RAM and disk before container work. Trigger when Docker Desktop or a container won't start, vmmem eats RAM or the Docker disk keeps growing; to set a WSL memory cap in .wslconfig; to list or install WSL distros; to bring a compose stack up or down; to prune images and build cache; to run a command in a container; to log in to a registry; or say dockerrunner (audit, check, up, down, prune, status, refresh). Local LLMs (Docker Model Runner too) are lmstudiorunner's; images comfyrunner's; VMs and sandboxes hypervrunner's; Docker's MCP catalog its MCP Toolkit's; registry tokens keywarden's.

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

Audits what Claude may do (permission rules, hooks, MCP scope, an agent's grants) and maps what it reaches on disk. Trigger on audit my permissions, why was this allowed, what stalls a routine, swap an allow for a deny, is this hook safe, gate my git pushes, a guard hook or call cap, PowerShell twins of Bash denies, where a rule should live, what is eating my disk, where has Claude been, config drift from a repo copy, skills loading twice; or say gatewarden (audit, harden, explain, scan, hooks, capreview, layout, map, footprint, drift, loads, status, refresh). Installs are trustwarden's; tokens keywarden's; secrets shieldwarden's; standing config rigwright's; agent design agentwright's.

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

Build a shared brand identity through structured interviews across multiple sessions. Explore purpose, audience, personality, and voice, reconcile founders’ perspectives, and produce a brandbook that designers, writers, and other collaborators can use.

• Define the identity of a new brand
• Clarify positioning during a brand refresh
• Align multiple founders’ perspectives

Develop a written brand identity through structured interviews across multiple sessions. Save answers and progress, explore founders' perspectives, and produce a master brandbook that gives designers, writers, and collaborators a shared reference.

• Defining the identity of a new brand
• Revisiting a brand's market positioning
• Preparing a brief for designers and writers

Run sequential reviews of a plan from business, design, engineering, and developer experience perspectives. Apply six principles to intermediate decisions, then bring close choices, scope questions, and reviewer disagreements to a final approval step.

• Reviewing a plan from several perspectives
• Running reviews without answering every intermediate question
• Considering close choices and disagreements at final approval

Check a Ruflo installation for common environment and configuration problems, then run automatic repairs. The checks cover software versions, background services, the memory database, API keys, MCP servers, disk space, and TypeScript.

• Checking the environment after installing Ruflo
• Diagnosing configuration and connection problems
• Repairing the memory database

Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.

• Index ADRs imported from another project
• Refresh a graph that differs from files on disk
• Set up ADR tracking in an existing codebase

Find background music, sound effects, images, and icons from existing assets, shared caches, or HeyGen. Save selected files locally and register them in an inventory, giving the agent a usable file path.

• Finding background music and sound effects for a video
• Sourcing background images and icons
• Registering existing assets in an inventory

Plan and review fluid simulations with FluidSim, from solver selection and resource estimates to output analysis and restart checks. Examine numerical accuracy through grid and time-step comparisons, conservation checks, and explicit limits on computing resources.

• Selecting a solver and reviewing simulation parameters
• Estimating memory, disk space, and runtime needs
• Inspecting spectra and conservation budgets

Build an evidence-backed incident timeline in a CTF sandbox by correlating logs, network captures, and other artifacts. Trace attacker actions across sources, distinguish confirmed events from inferred gaps, and preserve the sequence that supports the conclusion.

• Combine logs and network captures into an incident timeline
• Trace attacker actions from initial access to persistence
• Separate confirmed event order from inferred gaps

Investigate how compiled or obfuscated programs work, including binaries, APKs, WASM, and firmware. Combine file inspection, decompilation, and observed execution to understand control flow, validation logic, and mechanisms that hinder analysis.

• Understanding unfamiliar compiled programs
• Investigating obfuscation and anti-debugging logic
• Solving CTF validation challenges

Create incident response runbooks with ordered recovery steps, severity levels, escalation contacts, and status update templates. Help on-call engineers follow clear procedures during outages, verify recovery, and keep stakeholders informed.

• Writing a payment service outage runbook
• Documenting database incident recovery
• Preparing guides for new on-call engineers

Build a PowerPoint file with Python when no Office app is open. It uses python-pptx, applies a supplied firm template when available, and saves the deck locally with a path for collection by the surrounding workflow.

• Creating slides in an environment without an open Office app
• Building a deck from a supplied firm template
• Delivering model-based slides as a local file

Generate an Excel workbook file in an agent session without an open Office app. Use Python and openpyxl to organize inputs, formulas, and checks, then save the .xlsx file and return its relative path.

• Creating an Excel file without opening Office
• Keeping model inputs and calculations on separate sheets
• Adding a sheet for financial consistency checks