4,624 skills sorted by stars.
Audit any repo against the agentic-quality doctrine — score entry docs, structure, and enforcement gates, then map each...
One-command GitHub repository health audit. Checks for missing standard files, GitHub configuration, branch protection,...
Run one offline hygiene pass over a repository and report findings with severity as a table, JSON or SARIF with a CI exi...
Scan GitHub for repos trending in the last 24 hours (vibe coding, AI coding, AI memory, vulnerabilities) via Exa/Firecra...
Use before a tag, GitHub release, or Zenodo archive, when README, CATALOG, CHANGELOG, CITATION.cff, the disclosure aggre...
Sanitize a private Hermes or agent repo for secure sharing or open-sourcing — scan for credentials, replace with placeho...
Initialize GitHub repositories with standard files and configuration. Generates LICENSE, CONTRIBUTING.md, SECURITY.md, i...
Generate a NullPointer Studio styled PDF penetration test report from findings.json. Produces a professional dark-themed...
Generate professional audit reports with structured findings, severity classifications, proof-of-concept code, and actio...
Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first wri...
Assign a defensible severity to a finding — build the CVSS 3.1 vector from demonstrated impact and reconcile it with the...
Structure a professional penetration-test report (engagement deliverable, not a single bug). Load at the end of a pentes...
比较多次执行记录的输入指纹、代码版本、依赖版本、配置指纹、运行环境、随机种子和输出指纹，适用于分析结果复现验收和环境漂移诊断。
Generates CVE request packages from pentest findings. Reads cve-candidates.json (auto-generated at pentest completion) o...
Detects permission requests triggered at app launch or before meaningful user interaction, which violates Guideline 5.1....
Close consequential product, behavior, data, permission, compatibility, and acceptance decisions through an evidence-fir...
Boost retrieval precision by reranking candidate passages with Cohere, BGE-Reranker, or cross-encoders.
Vulnerability-research loop toward a novel CVE. Target triage -> attack-surface map -> ranked hypotheses -> investigate...
Researches a question with independent parallel specialists that gather evidence from the code, its history, and primary...
Check, audit, draft and review research documents (papers, theses, reports, proposals) in any field, in LaTeX, Markdown,...
Research: structured investigation, fact-checking, explanation traces.
Use when a Research Architect project has an evidence-ready spine, evidence and claim trail, citation support, terminolo...
Researches malware analysis, CVEs, attribution reports, and hacker community sources. Use when the album subject involve...
审核服务或工具操作的单次超时、重试次数、退避、随机抖动、错误分类、熔断器、幂等键、失败补偿和最坏总耗时，适用于可靠性策略发布前检查。
Use before evaluations or after roster churn to resolve live policy versions and restore the champion flag.
Respond to a potentially compromised user account. Use when impossible travel, credential stuffing, successful phishing,...
Respond to a malware incident following PICERL methodology. Use when malware is detected on endpoints. Orchestrates tria...
Respond to a reported phishing email following PICERL methodology. Use when a phishing email is reported or detected. An...
Respond to a ransomware incident following PICERL methodology. Use when ransomware is detected or suspected. Orchestrate...
Use to govern how deployed AI autonomy matures over time, at the Learn-phase cycle review and as a standing Responsible...
Use when narrowing access that sharing already granted. Trigger keywords: restriction rule, recordFilter, userCriteria,...
Este skill deve ser usado para reescrever currículos com foco em compatibilidade ATS e impacto para recrutadores, e/ou a...
Use when a user wants to audit a resume for unsupported claims, inflated ownership, inconsistent dates or metrics, weak...
Apply Retell AI security best practices for secrets and access control. Use when securing API keys, implementing least p...
Designs and audits retrieval: full-text search, pgvector recall, hybrid RRF fusion, reranking, chunking, recall quality...
Extract and analyze device firmware to find hardcoded secrets, backdoors, vulnerable services, and the real version behi...
Deep reverse engineering in IDA Pro — Hex-Rays decompile, cross-references, types, patching — via the GUI or the ida-pro...
Reverse front-end JavaScript end to end: trace which script fires a given request, capture a signing/encryption function...
Reverse macOS Mach-O binaries and .app bundles — codesign/notarization state, entitlements, Objective-C/Swift symbol rec...
Reverse a custom network protocol from captured traffic or the client binary: recover the frame layout, message-type dic...
Security-test a desktop thick client end to end: map its trust boundaries, then work the local attack surface (config fi...
- IDAPython (IDA Pro scripting)
Structured code review that reports correctness, security, performance, and maintainability findings before any fix. Use...
Request a read-only adversarial Codex review with explicit model, effort, budget, and compact findings.
review this, pre-landing review, check my code, review before merge, code review, look over my changes, audit this PR, r...
Deep code review - security, performance, architecture, and actionable fixes
Full QA review pipeline covering security audit (OWASP Top 10), performance analysis, accessibility check (WCAG 2.1 AA),...
Harmonia review stage - hierarchical review under the review lead with gates and receipts. Use ONLY when explicitly invo...