Menu
SkillsMP has collected 10 skills from awslabs/agentic-developer-platform. Open a skill to review its source and details.
Showing 10 of 10 collected skills.
Emit AIDLC inception artifacts as GitHub issues: one EPIC per intent, one child per AIDLC unit, natively sub-issue-linked, each in the repo's mandatory five-section format with deterministic Validation gates. Delivery loop generation is a two-stage protocol:…
Delegate a single bounded coding or code-review task to the OpenAI Codex CLI (runs against Bedrock), then review Codex's output yourself before committing. ONLY use this skill when the triggering issue or comment EXPLICITLY names Codex — e.g. "use Codex",…
Analyze a suspicious URL by visiting it in an isolated AgentCore Browser session. Captures screenshots, DOM, network requests, redirects, and extracted IOCs. Use for phishing triage, suspicious-link investigation, and malicious-site fingerprinting.
Static analysis of a malware sample inside the sandboxed worker — PE/ELF/Mach-O parsing, IAT + suspicious API combinations, embedded resources, YARA scanning against Florian Roth's corpus, anti-analysis detection, family-specific config extraction. Use this…
Consult OSINT sources and synthesize a prior hypothesis that steers downstream analysis. M1 scope is MalwareBazaar (no auth, no vault dependency) + web search + MITRE ATT&CK; VirusTotal + Shodan + urlscan are commented out in the skill until vault credentials…
Lightweight fingerprinting of a malware sample — hashes, file type, entropy, strings, candidate IOCs. Use this skill whenever you start a 7-stage malware analysis pipeline, need a quick file identification before deeper analysis, or want to check a sample…
Detonate the sample in CAPE's instrumented Windows VM and retrieve the behavioral report — file/registry events, network callbacks, process injection chains, dropped payloads, API trace, screenshots, timeline. Use this skill whenever static analysis alone…
Cross-reference dynamic findings against threat intel (MISP, VT, web reporting) + MITRE ATT&CK to derive family + TTPs + campaign linkage. Use this skill whenever you have Stage 4 dynamic observations (C2 IPs, mutexes, injection targets) and want to link them…
Synthesize severity (malicious/suspicious/benign), confidence (high/medium/low), STIX 2.1 IOC bundle, CSV feed, and concrete recommended actions (host isolation, token revocation, perimeter blocks, fleet-wide hunt queries) from all prior stage envelopes. Use…
Produce the final deliverables — executive summary (for leadership), structured technical report (for IR), STIX 2.1 + CSV IOC feeds (for SIEM/firewall), copy-pasteable Splunk/Elastic/Sentinel hunt queries — upload them all to S3 with presigned URLs, and post…