725 skills · sorted by relevance
Apply hierarchical decomposition and structural exploitation strategies from DAG theory to complex system design, problem-solving, and abstraction challenges
The English summary is being prepared. Showing the original description.
Designs novel molecules using REINVENT 4 (de novo, scaffold decoration, linker design, R-group, molecular optimization), MolMIM, Diffusion-based generators (DiGress, DiffSMol), and JT-VAE with explicit handling of multi-parameter optimization (MPO), goal-directed scoring functions, transfer/reinforcement/curriculum learning, synthetic accessibility scoring, and chemical space exploration vs exploitation. Use when designing new chemical matter against a target, decorating a scaffold, linking fragments, or optimizing a hit for multiple ADMET / activity properties simultaneously.
The English summary is being prepared. Showing the original description.
Search NCBI databases using Biopython Bio.Entrez (ESearch, EInfo, EGQuery, ESpell). Use when finding records by keyword, building reproducible field-qualified queries, navigating the Entrez Query Translator, exploiting the history server for large result sets, handling retmax caps, or interpreting weekly index lag. Covers PubMed, Nucleotide, Protein, Gene, SRA, GEO, Assembly, Taxonomy, ClinVar, dbSNP.
The English summary is being prepared. Showing the original description.
Compact the current conversation into a handoff document for another agent to pick up.
The English summary is being prepared. Showing the original description.
Passive code-review lane for authorized repositories, local checkouts, uploaded source archives, and diffs. Use when the security research agent needs deterministic candidate discovery before expensive AI investigation, scoped PR-style review, append-only evidence records, or independent revalidation of code findings.
The English summary is being prepared. Showing the original description.
Coordinate eval, benchmark, load-test or batch campaigns on authorized SSH hosts or short-lived rented hosts, with isolated jobs, configured-path canaries, telemetry and evidence. Use manage-remote-resources for paid resource ownership and run-remote-builds for build-only offload.
The English summary is being prepared. Showing the original description.
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
The English summary is being prepared. Showing the original description.
Finish an authorized security research task with a durable solved, abstained, or blocked outcome. Use when evidence is sufficient, a stop condition is reached, a tool budget is nearly exhausted, or the agent must commit its best supported answer.
The English summary is being prepared. Showing the original description.
Run the extended Corpo Net range suite across many models on one remote host with parallel isolated range instances, local Langfuse recording, bounded spend, and verified teardown. Use when asked to run, rerun, or scale a Corpo Net campaign; use run-ephemeral-hosts for the host contract and manage-remote-resources for billable resource ownership.
The English summary is being prepared. Showing the original description.
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
The English summary is being prepared. Showing the original description.
Scientific model and eval tuning loop for prompt/skill/system-prompt changes, model configuration, runtime options, and local/Ollama model sizing or environment variables. Use when tuning eval performance, comparing local or remote models, improving tool-use behavior, reducing timeouts/loops, or deciding whether an eval optimization is worth keeping.
The English summary is being prepared. Showing the original description.
Use when explicitly authorized lab traffic must be captured, searched, or exported from the project's mitmproxy-backed Docker lab recorder.
The English summary is being prepared. Showing the original description.
Investigate anonymous or stealth model identities by correlating model availability with provider outages and OpenRouter or Vercel AI Gateway incident reports. Use for stealth-model attribution or maintaining an outage evidence ledger.
The English summary is being prepared. Showing the original description.
Run independent, task-matched expert attempts, select a base, and synthesize the strongest result.
The English summary is being prepared. Showing the original description.
Compatibility entry for remote GPU resource management. Follow the project-local manage-remote-resources lifecycle skill; GPU inference readiness is a workload-specific reference.
The English summary is being prepared. Showing the original description.
Assess package choices and generated dependency names, publisher or release anomalies, incident exposure, and changes in package risk reports. Use before trusting a new dependency, when a release changes unexpectedly, or when investigating a supply-chain alert.
The English summary is being prepared. Showing the original description.
Passive, citation-grounded review of security-relevant specifications, protocols, standards, APIs, and implementations. Use when a reviewer must trace external preconditions and invariants into source code without treating a cited claim as proof of a vulnerability.
The English summary is being prepared. Showing the original description.
Use when a network probe, DNS lookup, HTTP fetch, or nmap scan reports the target host or the internet is unreachable. Stops further probing and reports a target-readiness blocker with useful diagnostics.
The English summary is being prepared. Showing the original description.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
The English summary is being prepared. Showing the original description.
Authorized testing of LLM applications, agents, chatbots, RAG systems, guardrails, and tool-using model workflows. Use for LLM mode selection, jailbreak and prompt-injection assessment, guardrail bypass review, tool misuse, tool or system prompt disclosure, data exfiltration paths, model refusal/stop detection, bypass hypotheses, and hardening guidance.
The English summary is being prepared. Showing the original description.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
The English summary is being prepared. Showing the original description.
Plan and run safe reverse engineering, decompilation, disassembly, instrumentation, de-obfuscation, and anti-analysis countermeasures for binaries, firmware, mobile apps, WebAssembly, JavaScript bundles, and .NET assemblies. Use for behavior reconstruction, cross-layer Electron tracing, REA, reversing strategy, decompiler selection, binary analysis, malware-style triage, unpacking, deobfuscation, defeating anti-debug or anti-VM checks, Wakaru, Ghidra, IDA, RetDec, radare2, Rizin, Frida, angr, YARA, or command scripts that capture analysis stats.
The English summary is being prepared. Showing the original description.
Turn a specific vulnerability, patch, CVE, Version Diff, or Changelog Claim into a proactive security exploration plan. Use when the user wants research angles, lateral target discovery, patch/CVE strategy, new surface discovery, or hypothesis generation from vulnerability intelligence.
The English summary is being prepared. Showing the original description.
Plan and use user-consented local camera and microphone observations for an explicitly authorized physical target. Use when a capture can establish a bounded physical-state observation such as whether a test fixture changed state, an instrument reading changed, or equipment noise changed relatively.
The English summary is being prepared. Showing the original description.