aibot88
- 8.3k skills
- 0 followers
- 3 repo stars
- 2 weeks ago last updated
- ▌ Baseline And Review Repository Secret Findings With Detect S · aibot88 bundleScan a repository for secrets, keep an auditable baseline, and review only newly introduced findings during commits or CI checks.
- ▌ Benchmark Prompt Injection Attacks Defenses And Recovery Pip · aibot88 bundleRun structured prompt-injection attack and defense experiments against an LLM-integrated app before production by measuring attack success and testing detection or recovery pipelines.
- ▌ Block Unsafe Agent Actions And Scan Newly Added Skills With · aibot88 bundleAdd a runtime guard that evaluates agent actions, blocks dangerous commands or secret exposure, and audits new skills before they run.
- ▌ Broker API Credentials To AI Agents Without Exposing Raw Key · aibot88 bundleStore credentials once, then inject them into outbound agent requests at runtime so agents can call services without receiving raw secrets.
- ▌ Browse Search And Cost Audit Local Coding Agent Histories Be · aibot88 bundleIndex local coding-agent sessions into a searchable SQLite-backed view so you can inspect usage, compare failures, and recover prior context quickly.
- ▌ Capture Linux Runtime Security Events And Suspicious Behavio · aibot88 bundleWatch live Linux and container activity through eBPF so you can triage suspicious runtime behavior before it disappears into guesswork.
- ▌ Catch Agent Era CI CD And Permission Misconfigurations Befor · aibot88 bundleRun Ship Safe before a release when an agent needs one pre-ship pass for CI/CD misconfigurations, permission risks, secrets exposure, MCP-related hazards, and dependency issues.
- ▌ Co Author Structured Docs With Staged Context Gathering And · aibot88 bundleUse Anthropic's doc-coauthoring skill to run a disciplined writing workflow instead of freeform drafting. The agent gathers missing context, iterates section by section, and pressure-tests the final document with reader-style review before teammates see it.
- ▌ Coordinate Human In The Loop Agent Teams In Auditable Matrix · aibot88 bundleRun manager-worker agent collaboration in Matrix rooms where humans can watch, intervene, and keep credentials out of worker hands.
- ▌ Decode Inspect Sign And Verify Jwts While Debugging Auth Flo · aibot88 bundleDecode JWTs, inspect claims, and verify or sign tokens with local keys during auth debugging and test setup.
- ▌ Deploy An Agent Readable Openclaw Defense Matrix And Hardeni · aibot88 bundleUse an agent-facing OpenClaw security guide to audit a live setup, surface conflicts, and apply a bounded hardening defense matrix with explicit approval gates and nightly checks.
- ▌ Detect Repository Licenses Before Dependency Approval Or Ope · aibot88 bundleUse Licensee when an agent needs to inspect a repository and determine what license text it actually matches before a dependency is approved or a codebase is redistributed. The skill is about evidence-backed license detection, not legal advice or broader compliance automation.
- ▌ Diff Live Database Schemas Against Declarative SQL Before Sc · aibot88 bundleCompare checked-in SQL against live MySQL, PostgreSQL, SQLite, or SQL Server schemas and generate a reviewable apply plan before agents touch production databases.
- ▌ Encrypt And Decrypt Age Secrets With Hardware Backed Yubikey · aibot88 bundleUse age-plugin-yubikey when an agent needs age encryption tied to a physical YubiKey identity instead of software-only keys.
- ▌ Extract Data And Complete Workflows In Your Real Logged In B · aibot88 bundleUse bb-browser when an agent needs to inspect pages, pull data, or complete form-driven tasks inside the user's actual logged-in Chrome session. It is for browser work where normal HTTP fetches fail because the important context lives behind auth, cookies, or internal web apps.
- ▌ Gate Pull Requests With Targeted Diff Aware AI Security Revi · aibot88 bundleRun a Claude Code powered security review pass on trusted pull requests so suspicious auth, secret, injection, and unsafe logic changes surface before merge.
- ▌ Inspect Binary Hardening Flags And Exploit Mitigations With · aibot88 bundleCheck ELF or PE binaries for hardening gaps like NX, PIE, RELRO, stack canaries, and Fortify before release or incident review.
- ▌ Investigate Crowdstrike Falcon Alerts And Telemetry Through · aibot88 bundleUse falcon-mcp when an agent needs CrowdStrike Falcon detections, incidents, behaviors, threat intel, or read-only response context to triage a security event without leaving an MCP workflow.
- ▌ Lint Dotenv Files For Duplicated Keys And Unsafe Formatting · aibot88 bundleCheck dotenv files for duplicated keys, malformed values, and formatting mistakes before they break local runs or secret handoffs.
- ▌ Lint Kubernetes Manifests And Helm Charts For Security And R · aibot88 bundleRun a static policy pass over Kubernetes YAML before misconfigurations, missing limits, or risky defaults reach a cluster.
- ▌ Load Mbox Mail Archives Into Sqlite For Offline Search Audit · aibot88 bundleUse mbox-to-sqlite when an agent needs to work across an email archive as structured data instead of parsing one message at a time. The agent imports a mailbox into SQLite, then hands the resulting database to search, reporting, and cross-dataset workflows without depending on a live mail provider.
- ▌ Load Test HTTP Endpoints With Reproducible Attack Profiles A · aibot88 bundleRun constant-rate HTTP attacks, capture binary results, and generate reports or plots before capacity changes and releases.
- ▌ Manage Elevenlabs Agents As Versioned Local Config Files Ins · aibot88 bundleInitialize, authenticate, and edit ElevenLabs agent configs from local files when you want agent definitions in code review instead of only in a hosted UI.
- ▌ Migrate Mysql Sqlite Or CSV Data Into Postgresql With Repeat · aibot88 bundleMove data into PostgreSQL with declarative load files, built-in type conversion, and repeatable migration runs before one-off import scripts become cutover risk.
- ▌ Mirror Github Issues Pull Requests Commits And Releases Into · aibot88 bundleUse dogsheep/github-to-sqlite when an agent needs a local, queryable snapshot of GitHub activity instead of bouncing through the web UI or ad hoc API calls. The agent authenticates once, pulls the exact GitHub objects it needs, and leaves behind a SQLite database that can be inspected, joined, diffed, or handed to downstream tools.
- ▌ Mirror Openclaw Workspaces And Stream Encrypted Backups With · aibot88 bundleSync an OpenClaw workspace to your own cloud storage or push encrypted agent-system backups with OpenClaw-aware mailbox, mirror, and bisync modes.
- ▌ Normalize Article Metadata From Urls Before Generating Link · aibot88 bundleUses metascraper to turn a URL plus its fetched HTML into normalized fields such as title, description, author, date, publisher, and lead image. This is useful when an agent needs reliable preview or briefing data from a page without building a custom parser for every site.
- ▌ Package Docs Repos And Pdfs Into Installable Agent Skills Wi · aibot88 bundleTurn documentation sites, GitHub repos, and PDFs into installable agent skill packages when hand-authoring a reusable skill would be slow or inconsistent.
- ▌ Persist Reusable Coding Agent Memory Across Sessions With En · aibot88 bundleKeep searchable long-term memory for coding agents in a local SQLite store and expose it through MCP when sessions keep forgetting prior decisions, conventions, and useful findings.
- ▌ Preflight Agent Specs For Prompt Injection Risk Across Promp · aibot88 bundleDescribe an agent in `agent_spec.yaml`, run deterministic prompt-injection analysis, generate mitigations, and validate defenses before rollout.
- ▌ Prevent Broken Github Actions Workflows Before CI Runs With · aibot88 bundleUse actionlint when an agent needs to inspect GitHub Actions workflow files before a push or pull request lands. The skill checks syntax, expressions, action inputs, runner labels, cron patterns, and a few security footguns so the agent can stop bad workflow changes before CI burns time.
- ▌ Probe AI Agents For Dangerous Tool Chains And Execution Side · aibot88 bundleTest agent systems for graph-discovered tool-chain vulnerabilities, silent side effects, and multi-phase trust exploits before deployment.
- ▌ Probe Kubernetes Clusters For Exposed Attack Paths With Kube · aibot88 bundleAssess a Kubernetes cluster from the attacker viewpoint when an agent needs exposure-focused findings instead of a general cluster scanner listing.
- ▌ Probe Ml And LLM Systems For Regressions And Vulnerabilities · aibot88 bundleRun automated red-team and failure scans against an LLM or RAG app before users find the breakage.
- ▌ Provision OAUTH Capable Microsoft Agent Identities With Entr · aibot88 bundleCreate Microsoft Entra Agent Identity blueprints, principals, and agent identities with the right beta Graph permissions, sponsor rules, and sidecar-based auth patterns.
- ▌ Red Team Agent Workflows For Jailbreaks Prompt Injection And · aibot88 bundleRun local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.
- ▌ Run Agents In Disposable Microvm Sandboxes With Network Allo · aibot88 bundleLaunch risky agent work inside disposable microVMs when you need stronger isolation, sealed egress, and host-side secret injection instead of direct host access.
- ▌ Run Security Audits And Variant Analysis Workflows In Claude · aibot88 bundleUse curated Trail of Bits security skills inside Claude Code when the job is auditing, variant hunting, or fix verification rather than generic coding assistance.
- ▌ Scan Agent Skill Folders For Risky Patterns And Missing Safe · aibot88 bundleRun a pre-trust security pass over skill packs and prompt bundles before they get shared, merged, or deployed.
- ▌ Scan Agent Workflows For Tools MCP Exposure And Adversarial · aibot88 bundleUse Agentic Radar to statically scan agent workflows, map tools and MCP servers, generate shareable security reports, and optionally run adversarial runtime tests before rollout.
- ▌ Scan Agentic Codebases For Exposed Tools MCP Usage And Mappe · aibot88 bundleGenerate a reviewable security report for a supported agent workflow before deployment by scanning its code, tools, MCP usage, and known vulnerability surface.
- ▌ Scan Claude Code Configs For Secrets Permission Drift And Un · aibot88 bundleAudit a Claude Code setup before use by flagging hardcoded secrets, broad allow rules, risky hooks, and dangerous MCP server config.
- ▌ Scan Repositories For Shai Hulud 2 0 Supply Chain Indicators · aibot88 bundleCheck repositories and CI surfaces for Shai-Hulud 2.0 compromise indicators when the task is targeted supply-chain triage, not generic malware scanning.
- ▌ Score Open Source Repositories For Supply Chain Risk Signals · aibot88 bundleCheck a repository against OpenSSF security heuristics before you trust it as a dependency, approve it for use, or ship from it.
- ▌ Screen Packages And Agent Skill Repos For Malware And Supply · aibot88 bundleUse SafeDep Vet as a pre-adoption gate when an agent, maintainer, or CI pipeline is about to add a new dependency or import a skill repository and needs malware and policy signals first.
- ▌ Triage Pull Request Security Risks With Staged Threat Modeli · aibot88 bundleAnalyze a GitHub pull request for security impact, run targeted vulnerability-investigation skills when Stage 1 finds credible threats, and return a structured verdict instead of doing an ad hoc manual review.
- ▌ Turn Windows Event Logs Into Sigma Backed Threat Hunting Tim · aibot88 bundleParse Windows event logs into fast timelines and detection-rich outputs so agents can triage suspicious host activity, search for known patterns, and hand investigators reviewable artifacts.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Skill Comply · aibot88 bundle中文优先：用于技能合规检查相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
- ▌ AI LLM Safety · aibot88 bundleEnforces safe AI usage practices, prevents prompt injection, and ensures model safety
- ▌
- ▌
- ▌ Env Validator · aibot88 bundleEnvironment variable consistency validator. Checks GH_* vs GITHUB_* naming conventions, validates documentation matches code, and ensures deployment scripts correctly map secrets. Use proactively when modifying environment variables, updating CLAUDE.md, editing configure-secrets.sh, or changing the Env interface.
- ▌ Perl Security · aibot88 bundle中文优先：用于Perl安全相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Comprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, web security (XSS/SQLi/CSRF), and perlcritic security policies.
- ▌
- ▌
- ▌
- ▌ Cerna Analysis · aibot88 bundle> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
- ▌
- ▌
- ▌
- ▌
- ▌ Hook Framework · aibot88 bundleHook Framework do $100M Leads — 3 tipos de hook (dream outcome, problem, secret). Use para gerar headlines de LP, hooks de ads (especialmente short-form), subject lines de email, primeiras frases de copy.
- ▌ Scitex Dataset · aibot88 bundleUnified dataset-discovery API across 7 scientific repositories — OpenNeuro + DANDI + PhysioNet (neuroscience, BIDS + NWB), Zenodo + Scientific Data (general), GEO (gene expression), ChEMBL (pharmacology), ClinicalTrials.gov (medical). Public API — `fetch_all_datasets()` / `fetch_datasets()` / `format_dataset()` (OpenNeuro convenience) + `search_datasets()` / `sort_datasets()` (cross-source ranking) + domain submodules `neuroscience`, `general`, `biology`, `pharmacology`, `medical` + `database` (build & query a local unified SQLite index). 11 MCP tools — `dataset_search` (cross-source filter/sort), per-source fetchers `dataset_openneuro_fetch` / `dataset_dandi_fetch` / `dataset_physionet_fetch` / `dataset_geo_fetch` / `dataset_chembl_fetch` / `dataset_clinicaltrials_fetch`, local-db `dataset_db_build` / `dataset_db_search` / `dataset_db_stats`, and `dataset_list_sources`. (Zenodo / Scientific Data are reachable via Python API + CLI; no standalone MCP fetch tool yet.) Drop-in replacement for `openneuro-python`,
- ▌ Sqlite Analyst · aibot88 bundleSQLite Analyst is built around SQLite embedded database. The underlying ecosystem is represented by WiseLibs/better-sqlite3 (7,041+ GitHub stars). It gives an agent a more technical and reliable way to work with the tool than a thin one-line wrapper, using stable interfaces like local .db files, SQL queries, schema inspection, FTS, WAL, query plans and preserving […]
- ▌
- ▌
- ▌ Pentest Pfsense · aibot88 bundlePentest especializado para pfSense CE e Plus — cobre todas as superfícies de ataque a partir da rede externa e interna, mapeado ao PTES e ao código-fonte real do pfSense
- ▌ Snyk Agent Scan · aibot88 bundleScan your AI agents, MCP servers, and skills for security vulnerabilities from the command line. Snyk Agent Scan discovers and audits every agent component on your machine — detecting prompt injections, tool poisoning, toxic flows, malware payloads, and credential handling issues across 15+ distinct risk categories.
- ▌
- ▌
- ▌
- ▌ Pre Pr Checklist · aibot88 bundleBefore opening a pull request, run the project's check suite, scan the diff for things reviewers can't easily catch (debug code, secrets, missing tests), and draft a PR body.
- ▌
- ▌ Validate Feature · aibot88 bundleValidate a feature implementation: build, tests, compliance, quality
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Design API Design · aibot88 bundleDesign API endpoints: routes, request/response shapes, authentication, pagination, error responses, and versioning strategy.
- ▌
- ▌
- ▌
- ▌ Owasp Zap Scanner · aibot88 bundleOWASP ZAP Scanner is built around OWASP security tooling ecosystem. The underlying ecosystem is represented by zaproxy/zaproxy (14,896+ GitHub stars). It gives an agent a more technical and reliable way to work with the tool than a thin one-line wrapper, using stable interfaces like ZAP scanning, passive/active checks, auth contexts, alerts, HTTP spidering and preserving […]
- ▌
- ▌ Sf Connected Apps · aibot88 bundle<!-- Adapted from Jaganpro/sf-skills@ff1ab74 (MIT). This file layers Brite conventions from brite-salesforce/CLAUDE.md. -->
- ▌ Uphold Invariants · aibot88 bundleLoad relevant code quality reference files (architecture, testing, security, type design, etc.) and apply their invariants to the current task. ALWAYS invoke before designing, writing, or editing ANY code.
- ▌
- ▌
- ▌ Architect Critique · aibot88 bundle**Core Philosophy:** An architecture doc that passes all 5 axes is deployable. One that fails is a wish list. Find the failures before engineering starts.
- ▌ Dependency Fix NPM · aibot88 bundleAction findings from dependency-audit-npm. Detects npm / pnpm / yarn (classic or berry), respects Corepack, uses overrides / resolutions for transitive vulns. Local commits only.
- ▌
- ▌ Git Secret Scanner · aibot88 bundleDetects leaked secrets in Git repositories using pattern-based scanning with Gitleaks rule definitions and the GitHub Secret Scanning API. Identifies exposed API keys, tokens, and credentials across full commit history using git log --all -p analysis.