Results for “procfu”

Enforce code quality with Ruff in a controlled, iterative workflow: run checks with optional scope and rule overrides, apply safe and unsafe autofixes, review diffs, and resolve remaining findings.

Redacts, previews, and inserts sanitized agent session transcripts into GitHub PR/issue bodies for provenance.

LLM observability with Langfuse — tracing, evals, prompt management, cost tracking

Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model.

Provisioning infrastructure via cloud IaC (Terraform/OpenTofu/CloudFormation/Pulumi) and local dev environments (Docker Compose, env vars). Use for IaC design or multi-cloud provisioning.

Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model.

glm-rate-proxy（localhost:8787・CC CLIのGLM/MiniMaxバックエンドプロキシ）の診断・修復スキル。 プロキシが止まる・エラーが出る・MiniMaxフォールバック失敗等を診断し対処法を案内（ソース自動書き換えなし・確認後実行）。 「/proxy-doctor」「プロキシ直して」「GLMが使えない」「フォールバック失敗」「LLMエラー系（CLIが動かない・4xx/429多発）」等で発火。

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

Orchestrates Python data pipelines with Prefect flows, tasks, retries, caching, parallel execution, and deployments to work pools.

rate(http_requests_total[5m])

Add a redacted agent transcript section to GitHub PR or issue bodies during MarketingClaw agent-created PR/issue workflows.

Development with Perf: tools and best practices

Working Backwards PRFAQ challenge that stress-tests a product concept customer-first. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.

Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model.

Specialized CTF sandbox skill for analyzing prompt-to-tool chains, deployment drift, and supply-chain provenance in cloud, container, and CI/CD environments.

Foundational SPARQL patterns covering RDF querying, triple patterns, graph patterns, and semantic web fundamentals. Use when querying RDF data or working with knowledge graphs. This is the entry point for SPARQL development.

proptest — property-based testing for Rust (Hypothesis-style). Generates thousands of random inputs to find counterexamples to invariants, with shrinking to minimal failing case. Critical for crypto, parsers, state machines, and finance code where edge cases matter. Includes strategies (gen functions), regression tracking, and integration with cargo test. Alternative: quickcheck (simpler API, less powerful). USE WHEN: user mentions "proptest", "property-based test", "proptest!", "Strategy", "Arbitrary", "shrink", "quickcheck", "regression file", "fuzz-light", "proptest-derive" DO NOT USE FOR: Generic Rust unit tests - use `testing/rust-testing` DO NOT USE FOR: Fuzzing with mutator (cargo-fuzz, AFL) - use bitcoin/testing/fuzz DO NOT USE FOR: KMP property testing - use `testing/kotest` (has built-in property)

Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.

杜甫（古典诗人）认知与表达框架（压缩蒸馏）：沉郁、家国与民生句法、律诗起承转合… 触发：诗史、三吏三别 等。不伪造诗文；哀悼体尊重

Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.

Generates type-safe, async-first Python 3.11+ code with full type annotations, mypy strict mode, pytest test suites, and validation via black and ruff.

Analyzes prompt injection, retrieval poisoning, memory contamination, planner drift, and tool-boundary abuse in agentic systems, mapping trust boundaries and proving exploit chains.

Detect and respond to Adversary-in-the-Middle (AiTM) phishing attacks that use reverse proxy kits like EvilProxy, Evilginx, and Tycoon 2FA to bypass MFA and steal session tokens.

Use when implementing python functionality with production-grade patterns and safeguards.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Operate Heroku Postgres with a safe inspection-first workflow. Use when the agent needs to provision, inspect, attach, promote, back up, restore, diagnose, or reason about credentials and data movement for Heroku Postgres.

Monitor bonding curves, graduation progress, and trade analytics on Pump.fun

Guides a structured interview and repository research to clarify feature requirements, classify scope, and produce context artifacts for approval before design.

Automates PR review and CI auto-fix for GitHub and GitLab using the Composio CLI. Pulls diffs, fetches failing job logs, posts review comments, and loops fix commits until checks go green.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production.

Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.

Post-deploy smoke test combining all 5 tools (Sentry + Supabase + Firecrawl MCPs, plus the Langfuse and Playwright CLIs) into one workflow. Use when asked to: "verify deploy", "post-deploy check", "smoke test production", "check if deploy is healthy", "ship or rollback", "post-release check", "verify release", "deploy.

Patch packaged QClaw.app (no source code) by modifying app.asar frontend bundles. Use when users have older QClaw versions and need to: (1) make invite-code checks only active on localhost with DEV_MODE=true and bypassed in production, (2) remove visibility restrictions for `other` and `system-config` model providers, and (3) ensure these providers appear in the model vendor dropdown.

Analyzes DeFi protocol risk before deposit, decomposes headline APY into sustainable yield, emissions, and drag factors, and flags common rug-risk patterns in tokenomics, liquidity, and governance. Advisory only—no wallet access, no private key handling, no transaction signing, no on-chain execution.