Results for “fuse”

Retune a collection of skills for a new model using archived runs and controlled comparisons. Establish normal measurement variation, register success criteria before editing, and make targeted changes until measured behavior meets the criteria or a specific limitation is reported.

• Investigating skill regressions after switching models
• Measuring the effect of instruction changes
• Separating behavior improvements from normal run variation

Manage which n8n instance an MCP session targets when working across production, staging, teams, or clients. Guides instance switching, checks before credential changes, and recovery from unexpected missing data or ambiguous credential writes.

• Switching between production and staging
• Checking the target before credential changes
• Investigating unexpected missing data

Build custom calculation and parsing tools that an n8n AI Agent can call. This skill covers JavaScript or Python inputs, structured arguments, string results, tool descriptions, and fixes for invocation and output errors.

• Adding a calculation tool to an AI Agent
• Defining typed inputs for multiple arguments
• Fixing tool output type errors

Manage files in Google Cloud's Cloud Storage buckets, the containers that hold stored data. Upload, download, and organize content, configure access and time-limited sharing links, and manage storage lifecycle, costs, and data protection.

• Upload, download, and organize stored files
• Share files through time-limited signed URLs
• Review storage classes and lifecycle rules

Build and publish a browser demo for a supplied LoRA, a model adaptation for image or video tasks. Tailor the Gradio interface to its inputs and follow the model’s recommended settings on Hugging Face Spaces.

• Share a trained LoRA through a browser demo
• Build an interface tailored to image editing or video generation
• Apply recommended trigger words and generation settings

Route requests to general assistance, medical source checks, educational answers, structured learning, or registration and subscriptions. It considers the intended use rather than isolated medical words, and refuses high-risk requests such as individual diagnosis or prescription dosing.

• Separating general tasks from medical learning requests
• Routing document authority and version checks
• Choosing a workflow for medical explanations or structured study

Remove a community skill installed through the hub after showing every file path and receiving explicit confirmation. Check installation records, protect first-party plugin skills, and record the uninstall action with a timestamp for the audit trail.

• Completely removing an unused community skill
• Reviewing deletion paths before uninstalling
• Keeping an audit trail of skill removals

Manage community skills installed through legal-builder-hub by uninstalling, disabling, or re-enabling them. It checks installation records and file locations, requires explicit confirmation before file operations, preserves configuration by default, and logs each action.

• Uninstalling a community skill that is no longer needed
• Temporarily disabling a skill and its hooks or agents
• Re-enabling a previously disabled skill

Tests a specific Convex feature with sample data and simulated users, without deployment. It checks expected results, rejects unauthorized callers, and verifies that queries return only data belonging to the current user.

• Verifying a newly implemented Convex feature
• Checking that other users cannot modify owned data
• Testing rejection of unauthenticated requests

Review Word contracts for textual inconsistencies, business terms, and legal clauses while preserving the original wording and formatting. Produce clause-specific comments, an objective contract summary, consolidated review opinions, and a business flowchart based on the contract.

• Checking amounts, dates, and clause references
• Reviewing payment and acceptance terms
• Organizing risks in liability and termination clauses

Diagnose macOS app launch and trust failures by inspecting code signatures, app permissions, and Gatekeeper checks. Identify the failure category and get a minimal validation or repair sequence that distinguishes local development issues from distribution requirements.

• Investigating a macOS app that refuses to launch
• Checking invalid signatures or signing identities
• Diagnosing app permissions and sandbox mismatches

Create fluid animations where rounded shapes merge as they approach and separate as they move apart. SVG filters combine blur with a cutoff effect to form soft, connected shapes for backgrounds, loaders, or cursor effects.

• Adding fluid shapes to a page background
• Creating a merging-blob loading indicator
• Building a soft cursor effect

Work across multiple n8n instances through one MCP connection, the link used by an agent to call tools. Specify each operation’s target, verify where credentials will be stored, and recover when requests reach the wrong environment.

• Operate on production and staging with explicit targets
• Verify the destination before saving credentials
• Investigate unexpected NOT_FOUND errors

Build custom calculation and parsing tools that an n8n AI Agent can call. This skill covers JavaScript or Python inputs, structured arguments, string results, tool descriptions, and fixes for invocation and output errors.

• Adding a calculation tool to an AI Agent
• Defining typed inputs for multiple arguments
• Fixing tool output type errors

Create, edit, and analyze Word documents while preserving formatting. Work with tracked changes and comments, extract document text, and convert pages to images for visual review, with workflows tailored to new documents and existing files.

• Create a new Word document
• Revise business documents with tracked changes
• Add review comments to a document

Explore how a website provides data or handles actions, then turn verified methods into a reusable Skill package with SKILL.md and Python scripts. The workflow includes testing, installation, and execution when requested.

• Turn recurring website tasks into reusable Skills
• Investigate how a site loads its data
• Build a verified method for bulk data collection

Design and refine web interfaces around their audience, tasks, and brand tone. Covers typography, color, layout, motion, accessibility, and performance, with guided techniques for reviewing existing screens and preparing them for release.

• Establishing a design system
• Reviewing interface usability and accessibility
• Adapting layouts for mobile devices

Author and review GitHub Actions workflow YAML safely so syntactically-valid YAML can't ship a workflow that GitHub Actions refuses to run. USE FOR: editing, adding, or reviewing any file under .github/workflows/, writing run-name/name/if/env/run values that contain ${{ }} expressions, diagnosing a run that fails with 'This run likely failed because of a workflow file issue' and no jobs starting, deciding when a workflow scalar must be quoted, validating workflows with actionlint. DO NOT USE FOR: authoring application YAML unrelated to GitHub Actions, Azure Pipelines, GitLab CI, or non-workflow YAML. SCOPE: this skill covers *syntactic/structural* correctness of workflow YAML (quoting, parsing, actionlint); for *semantic and functional* workflow design (what a workflow should do, agentic-workflow behavior), see .github/agents/agentic-workflows.agent.md — the two are complementary. INVOKES: actionlint (downloaded pinned binary) plus git/grep for inspection.

The English summary is being prepared. Showing the original description.

Black-box security audit of a DEPLOYED AI agent (not the MCP server behind it) — tool-call hijacking, cross-session memory poisoning, confused-deputy via connected tools, agent-to-agent IDOR, excessive agency / unconfirmed destructive actions, and privilege compromise where the agent holds broader perms than the user. Use when the target is a live assistant/agent product with tool access (bookings, email, payments, file/RAG, browsing) rather than a raw LLM chat box or an MCP server you can read.

The English summary is being prepared. Showing the original description.

Security audit of Model Context Protocol (MCP) servers — tool poisoning, prompt injection via tool descriptions and results, unscoped/over-privileged tools, path traversal in file tools, command injection in shell/exec tools, SSRF in fetch tools, secret leakage through tool output, missing approval gates on state-changing actions, confused-deputy and rug-pull tool redefinition, token passthrough, and unsafe stdio/HTTP transport config. Covers auditing both first-party and third-party MCP servers (Python FastMCP, Node MCP SDK) and their client configs (Claude Desktop, Cursor, Cline, Windsurf, Zed). Use when reviewing, hardening, or hunting bugs in an MCP server, an agent's tool integrations, or a mcpServers config block. 中文触发词：MCP审计、工具投毒、提示注入、智能体安全、MCP服务器漏洞

The English summary is being prepared. Showing the original description.

Help users chaos test their app with mirrord: inject artificial latency or connection errors into a mirrord session's outgoing traffic via per-session chaos rules managed with the `mirrord chaos` CLI. Use when a user wants to add latency or delay to outgoing connections or a dependency (e.g. a slow database), simulate connection failures (reset, timed out, refused), test app behavior under degraded network conditions, or wire chaos rules into CI test runs. Always use this skill instead of the deprecated _experimental_.latency mirrord config option.

The English summary is being prepared. Showing the original description.

Cloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis. Covers IAM enumeration (aws iam, az role, gcloud iam), STS/AssumeRole chaining, Azure Managed Identity abuse (via SSRF/leak), GCP service account JSON abuse, IMDSv1/v2 attacks via SSRF, K8s ServiceAccount token privilege analysis once held (token discovery / cluster exposure is owned by hunt-k8s), role-trust-policy confused-deputy, cross-account assume-role enumeration, IAM privilege escalation patterns (24+ AWS, 8+ Azure, 6+ GCP), and AWS Cognito Identity Pool unauthenticated-role attack chain (GetId → GetCredentialsForIdentity → IAM role abuse). Built for the case where recon yields a credential (key, JSON, token) and you need to know what it grants and how to escalate. Use when an AWS key / Azure secret / GCP service account JSON / K8s SA token surfaces from a code repo, JS bundle, APK, breach corpus, or SSRF chain.

The English summary is being prepared. Showing the original description.

Detect and humanize AI-generated Chinese text. 20+ rule detection categories plus statistical features (sentence-length CV, short-sentence fraction, comma density, perplexity, GLTR, DivEye) plus scene-aware LR fusion (rule × 0.2 + LR × 0.8) trained on three scenes: general / academic / longform 长文本 (≥1500 字)。Unified CLI: ./humanize {detect,rewrite,academic,style,compare}. 8 style transforms (casual/zhihu/xiaohongshu/wechat/academic/literary/weibo/novel)。 Multi-paragraph rewriting (paragraph length CV、跨段 trigram 重复) plus best-of-N humanize (默认 N=10 取最低 LR)。165 replacement patterns + CiLin 同义词词林 38873 with collision blacklist。 Academic paper AIGC reduction for CNKI/VIP/Wanfang (知网/维普/万方 AIGC 检测降重)。 Pure Python, no dependencies, offline。v5.0.0 — HC3 fused 准确率 95%、学术 hero 100→35 (-65)、 工作汇报 96→13 (-83)、长篇博客 96→41 (-55)。 Use when user says: "去AI味", "降AIGC", "人性化文本", "humanize chinese", "AI检测", "AIGC降重", "去除AI痕迹", "文本改写", "论文降重", "知网检测", "维普检测", "AI写作检测", "让文字更自然", "detect AI text", "humanize text", "reduce AIGC score", "make text human-like", "去ai化", "改成人话", "去机器味", "降低AI率", "过AIGC检测", "长文本改写", "小说改写"

The English summary is being prepared. Showing the original description.

Use this skill to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the merged-since-last-tag diff), sanitize the [Unreleased] CHANGELOG block into a dated version block with one concise "so what" entry per merged PR (drop internal-only churn, consolidate duplicates), bump pyproject.toml + uv.lock, run the CI-mirror lint chain, and open the release PR. Activate on "ship a release", "cut v0.x", "release prep", "bump and PR", "open release PR", "what kind of release do we need", or any phrasing that ends in opening a release PR -- even when the user does not say "skill". Stops BEFORE tagging; tagging stays a human gate that triggers the release workflow. Refuses to bump to a major (>= 1.0.0) version without explicit operator confirmation.

The English summary is being prepared. Showing the original description.