291 skills · sorted by relevance
Use when inspecting .debug_info or .debug_line sections with dwarfdump or readelf, working with split-DWARF .dwo files, setting up debuginfod, or checking how LTO and stripping affect debug info.
The English summary is being prepared. Showing the original description.
Use when inspecting, searching, verifying, or parsing DWARF debug info: DIEs, DW_TAG_/DW_AT_ entries, .debug_* sections, line tables, or llvm-dwarfdump/readelf output.
The English summary is being prepared. Showing the original description.
Use when running GDB: breakpoints, watchpoints, segfault or hang debugging, reverse debugging, remote gdbserver, core dumps, pretty-printers, Python scripting, or multi-threaded debugging.
The English summary is being prepared. Showing the original description.
Fix scattered/torn regions in hex-grid simulated annealing layouts that use "competitive flood-fill" (one tile per region per outer iteration). Use when: (1) regions of >20 tiles end up dispersed instead of forming compact blobs, (2) maxDist/sqrt(N) dispersion ratio is 10×+ worse than the ideal compact blob, (3) tiles assigned to one region show up in multiple disconnected fragments across the layout, (4) the visualization has a "trypophobia ring" pattern at the perimeter where some regions spill into a perimeter spiral, (5) an overflow spiral fallback exists in the layout code and frequently kicks in for large regions, (6) bigger regions look worse than smaller ones (small regions stay compact, big ones shred). Root cause: interleaved competitive flood-fill (round-robin one tile at a time across all regions) lets large regions get boxed in by neighbors before they finish growing — the unfilled remainder is dumped into the overflow spiral at the perimeter, far from the seed. Fix: replace with sequential region-by-region BFS — process regions in size-descending order, fully claim each region's N contiguous tiles before moving to the next.
The English summary is being prepared. Showing the original description.
多卡分布式训练中的 loss/gnorm 精度溢出检测与根因追溯。基于 MSProbe dump 数据，先跨 rank 定位首次出现 NaN 的源卡，再在源卡上追溯具体的溢出根因算子。 当用户需要：(1) 多卡分布式训练场景下的 NaN/Inf 溢出检测 (2) 找出首先出现 NaN 的源卡 (3) 追溯根因计算算子 (4) loss/gnorm NaN 问题定位 时使用此 skill。
The English summary is being prepared. Showing the original description.
Use whenever the user mentions Betaflight, FPV drone firmware, flight-controller config, PID/filter/rates tuning, or blackbox log analysis — or shares a Betaflight artifact: a CLI diff/dump (lines like 'diff all', 'set ', 'feature ', 'resource ') or a .bbl/.bfl blackbox log, even when not named as such — or runs a chirp tuning session via Sweep Studio / FPVLogForge (a chirp log ID to analyse, 'analyse log', 'résultat chirp', iterative Bode/step/Ms tuning). Covers flight symptoms (oscillations, wobble, propwash, jello, hot motors, drift), motor/ESC and RX/ELRS/CRSF setup, builds from 3" to 10" (cinewhoop, tinywhoop, longrange, X-class), version migrations (4.4 → 4.5 → 4.6), and configuring a new drone from scratch (setup wizard). Trigger even when phrased casually ("mon drone wobble", "PID help", "config FC") — under-triggering is worse than over-triggering.
The English summary is being prepared. Showing the original description.
Manage LLM context windows deliberately — budgeting, prioritization, summarization, and retrieval instead of dumping everything in. Use when prompts grow long, costs rise, or the model loses track of key details.
The English summary is being prepared. Showing the original description.
Turn raw Lumen release content (a dump of the LedgerHQ/lumen GitHub Releases page) into one minimalist Slack announcement, drafted to #lumen-releases. Use whenever the user pastes one or more `@ledgerhq/lumen-*` package releases, a chunk of the Releases page, or asks to "announce", "format", "post", or "write release notes / a Slack message" for new Lumen versions. Trigger it even when the user just drops the raw release text with no instructions, or says things like "new Lumen release", "format these lumen versions for Slack", or "lumen changelog for the channel".
The English summary is being prepared. Showing the original description.
Identify and exploit misconfigured Spring Boot Actuator endpoints. This skill covers how to extract sensitive configuration details, heap dumps, environment variables, and ultimately escalating to Remote Code Execution (RCE) via `spring-cloud-starter` vulnerabilities.
The English summary is being prepared. Showing the original description.
Memory forensics playbook using Volatility 2/3. Use when analyzing memory dumps for malware analysis, credential extraction, process investigation, code injection detection, and incident response timeline reconstruction.
The English summary is being prepared. Showing the original description.
Identify and exploit GraphQL API vulnerabilities by leveraging Introspection queries to dump the entire database schema, performing query batching to bypass rate limits (brute forcing), and extracting deeply nested unauthorized data via graph relationship abuse.
The English summary is being prepared. Showing the original description.
Exploit Active Directory replication privileges (DS-Replication-Get-Changes) to perform a DCSync attack, allowing an attacker to impersonate a Domain Controller and extract password hashes (like the krbtgt hash for Golden Tickets) without code execution on a DC.
The English summary is being prepared. Showing the original description.
Execute a DCSync attack mimicking the behavior of a legitimate Active Directory Domain Controller (DC). Leverage Directory Replication Service Remote Protocol (DRSR) permissions to silently request and extract the password hashes (NTLM/Kerberos) of any or all users in the domain without executing code on the target Domain Controller.
The English summary is being prepared. Showing the original description.
Bug bounty findings secretary, tracker, and workspace initializer for the bb-huge portal. Use this skill for web security research, vulnerability hunting, and hunt workspace setup. Triggers on: "log finding", "save finding", "add to bb-huge", "record vulnerability", "update finding", "show findings", "bb-huge stats", "mark as confirmed", "mark as rewarded", "setup workspace", "pull evidence", "continue working on finding", "dump attachments", "list my skills", "what skills do I have", "/bb-huge init", "init hunt workspace", "new bug bounty program", "start hunting", "mobile bug bounty", "binary analysis", "source code review", "white-box audit", "h1-brain", "hack program", "hack()", "search disclosed", "fetch rewarded". Also auto-activates whenever a vulnerability is discovered during any recon, fuzzing, or manual testing session — do not wait to be asked.
The English summary is being prepared. Showing the original description.
Execute a complete Active Directory penetration test from initial enumeration to domain dominance. Use this skill for AD security assessments including LDAP enumeration, Kerberos attacks (Kerberoasting, AS-REP roasting), BloodHound attack path analysis, credential dumping with Mimikatz, lateral movement via PsExec/WMI/DCOM, DCSync for NTDS extraction, and Golden/Silver ticket forging. Covers the full kill chain from domain user to domain admin.
The English summary is being prepared. Showing the original description.
Identifies and unpacks packed binaries: detecting packers from section names and entropy, automatically unpacking UPX, and manually unpacking custom packers by finding the OEP and dumping. Activates for requests to unpack a packed sample, detect a packer, or recover the original binary from UPX or a custom packer.
The English summary is being prepared. Showing the original description.
Extracts indicators of compromise from raw analysis artifacts: parsing strings dumps, sandbox reports, PCAP summaries, and logs for URLs, domains, IPs, hashes, mutexes, and file paths, then deduplicating and typing them. Activates for requests to extract IOCs from analysis output, pull indicators from a report, or harvest atomic indicators.
The English summary is being prepared. Showing the original description.
Manually unpacks a runtime-packed Windows binary by finding the original entry point (OEP) through tail-jump and entropy analysis, then guiding a memory dump at OEP. Activates for requests to manually unpack a sample, find the OEP, or unpack a custom/unknown packer that generic tools cannot handle.
The English summary is being prepared. Showing the original description.
Uses x64dbg to dynamically debug Windows malware: setting strategic breakpoints on APIs, stepping through unpacking and decryption, dumping memory at the right moment, and manipulating execution to reach hidden code. Activates for requests to debug malware with x64dbg, set API breakpoints, or step through unpacking in a debugger.
The English summary is being prepared. Showing the original description.
Analyzes a memory image with Volatility 3 to find malware: rogue processes, injected code, suspicious network connections, loaded modules, and persistence, then extracts artifacts for further analysis. Activates for requests to do memory forensics, analyze a RAM dump, or hunt malware in memory with Volatility.
The English summary is being prepared. Showing the original description.
Obsidian Claw is an ontology-building skill that transforms chaotic notes, raw ideas, voice dumps, and meeting transcripts into a structured, interlinked knowledge base inside Obsidian. Use this skill whenever the user wants to: add new notes to their Obsidian vault and auto-link them to existing ones, build a concept graph or knowledge map, surface forgotten related discussions ("you talked about this with investor X 3 months ago"), extract entities and relationships from unstructured text, or turn scattered thoughts into wiki-style atomic notes. Also trigger when the user mentions "second brain", "Zettelkasten", "PKM", "personal knowledge management", "note graph", "knowledge graph", "link my notes", "organize my vault", "connect ideas", or asks Claude to "remember" something across sessions using Obsidian. If the user is doing anything with Obsidian notes and wants intelligence layered on top, use this skill.
The English summary is being prepared. Showing the original description.
Pixel-faithful clone of any web UI into the user's existing stack, using whatever sources are available — a screenshot alone, a live URL, raw HTML/CSS, or any combination. Use this skill whenever the user wants to recreate, match, replicate, or "clone" a design from a screenshot, image, URL, Figma export, or HTML dump. Trigger on phrases like "clone this", "match this design", "build this from screenshot", "recreate this page", "make it look like this", "rebuild this UI", "copy this layout", or any time the user provides a visual reference and asks for a faithful implementation. Do not undertrigger — even if the user just drops a screenshot without explicit phrasing, this skill applies.
The English summary is being prepared. Showing the original description.
Cognitive copilot for people with ADHD. Use this skill whenever someone mentions paralysis, can't start a task, feels overwhelmed, needs to organize their day, is procrastinating, doing a brain dump, wants to plan their week, or says anything like "I don't know where to start", "I have too much on my plate", "I can't focus", "I'm stuck", or "I finished X but can't start Y". Also triggers on general focus and productivity requests — don't wait for the user to explicitly say "ADHD". If someone seems stuck, scattered, or overwhelmed, this skill applies.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to 'plan my day', 'help me plan today', 'morning planning', 'what should I work on today', 'daily planner', 'evening reflection', 'reflect on my day', 'migrate tasks', 'carry tasks forward', 'rapid log', 'brain dump my tasks', or mentions ADHD-friendly planning, time-blindness, swim lanes, energy-based task management, bullet journal for ADHD, or dopamine menu. Provides a BuJo-style daily planning system with swim lanes, migration, reflection, and dopamine rewards. Part of the ADHD-founder.com ecosystem.
The English summary is being prepared. Showing the original description.