jeremylongshore

Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy,…

Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or…

Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before / interrupt_after and Command(resume=...) — JSON-serializable state, clean resume semantics, and UI wiring for approval decisions. Use when adding an approval gate before an expensive…

Build reliable dev / staging / prod isolation for LangChain 1.0 services — Pydantic Settings + SecretStr, cloud Secret Manager in prod, per-env prompt and model version pinning, env-specific checkpointer and observability. Use when graduating from .env-in-dev…

Compose LangChain 1.0 Python runnables with the production defaults the docs do not warn about: parallel batching, narrow fallbacks, and brace-safe prompts. Use when building an LCEL chain with RunnableSequence / RunnableParallel, adding resilience via…

Survive the rate-limit failure modes that crater production Podium integrations — cascading 429s that burn the daily quota by lunch, ignored Retry-After hints, silent daily-quota breaches, per-endpoint budget exhaustion, end-of-day review-request bursts, and…

Probe a target for accidentally-served secret-bearing files in the web root — .git/, .env, .DS_Store, backup files, database dumps, key files, CI configs, IDE configs. Use when: post-deploy verification on a new release, or SOC2 auditor asked "what's…

Generates customized business agreements for 10 common relationship types with plain English annotations. Use when formalizing a business relationship, creating a partnership agreement, or drafting a service contract from scratch. Trigger with…

Implement user sign-up and sign-in flows with Clerk. Use when building authentication UI, customizing sign-in experience, or implementing OAuth social login. Trigger with phrases like "clerk sign-in", "clerk sign-up", "clerk login flow", "clerk OAuth", "clerk…

Implement session management and middleware with Clerk. Use when managing user sessions, configuring route protection, or implementing token refresh and custom JWT templates. Trigger with phrases like "clerk session", "clerk middleware", "clerk route…

Configure enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls. Trigger with phrases like "clerk SSO", "clerk RBAC", "clerk…

Create your first authenticated request with Clerk. Use when making initial API calls, testing authentication, or verifying Clerk integration works correctly. Trigger with phrases like "clerk hello world", "first clerk request", "test clerk auth", "verify…

Install and configure Clerk SDK/CLI authentication. Use when setting up a new Clerk integration, configuring API keys, or initializing Clerk in your project. Trigger with phrases like "install clerk", "setup clerk", "clerk auth", "configure clerk API key",…

Use when two or more agent sessions — same or different platforms (Claude Code, Codex, Gemini CLI, Copilot, Cursor) — work the same repo concurrently, hand off in-flight work, or need to interrogate each other about a handoff. Triggers: "set up comms with the…

Create production-grade agent skills aligned with the 2026 AgentSkills.io spec and Anthropic best practices (2026). Also validates existing skills against the Intent Solutions 100-point rubric. Use when building, testing, validating, or optimizing Claude Code…

Validate a SKILL.md file against the four-tier validation system: Tier 0 (locate), Tier 1 (standard or marketplace grading per the IS 100-point rubric), Tier 2 (static production gate — allowed-tools accuracy, auth protocol, dead code, tool safety,…

Generate and configure Nixtla Skills using the CLI for forecasting workflows. Use when installing or updating skills. Trigger with 'install nixtla skills' or 'update nixtla'.

Generate benchmarking pipelines to compare forecasting models and summarize accuracy/speed trade-offs. Use when evaluating TimeGPT vs StatsForecast/MLForecast/NeuralForecast on a dataset. Trigger with "benchmark models", "compare TimeGPT vs StatsForecast", or…

Research and summarize Nixtla ecosystem updates and time-series forecasting content from the web and GitHub. Use when gathering release notes, recent changes, or best-practice references. Trigger with "Nixtla updates", "what's new with TimeGPT", or "find…

Generate production-ready TimeGPT forecasting pipeline code from requirements. Use when scaffolding a pipeline with validation, logging, visualization, and repeatable runs. Trigger with "create TimeGPT pipeline", "build TimeGPT integration", or "generate…

Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series experiments. Trigger with "baseline review",…

Orchestrate 6-phase changelog generation workflow with AI synthesis, multi-source data fetching (GitHub/Slack/Git), quality validation, and automated PR creation. Use when automating release notes, weekly changelogs, or documentation updates. Trigger with…

Analyze and explain TimeGPT forecast results in plain English. Generates executive summaries with driver analysis. Use when stakeholders need forecast explanations, board presentations, or compliance documentation. Trigger with "explain forecast", "why is the…

Fine-tunes TimeGPT on custom datasets to improve forecasting accuracy. Use when TimeGPT's zero-shot performance is insufficient or domain-specific accuracy is needed. Trigger with "finetune TimeGPT", "train TimeGPT", "adapt TimeGPT".

Self-improving research loops with hypothesis generation, experiment design, and result analysis

Full-stack research and code generation pipeline - research, code, and create

Natural language web UI control — element detection, targeted interaction, and automated form filling

Public opinion analysis and sentiment at scale — sentiment scoring, stance detection, and multi-dimensional bias measurement.

Meta-specialist that auto-discovers and scaffolds new specialists from trending GitHub repos

Safe multi-language code execution via alibaba/OpenSandbox

Multi-agent financial analysis pipeline: fundamental analysis, technical indicators, and news sentiment scoring for any ticker symbol. Wraps patterns from virattt/ai-hedge-fund and ZhuLinsen/daily_stock_analysis.

Ensemble predictions via swarm intelligence with multi-model voting and consensus

Generates conventional commit messages from staged git diffs. Activates when the user requests a commit message and produces type(scope) subject format.

Runs the j-rig seven-layer binary evaluation on a Claude skill and reports a ship or no-ship rollout decision. Activates when a user asks to evaluate, grade, score, or gate a SKILL.md before release.

Generates comprehensive analysis reports from input data. Activates when analysis is requested and produces structured output.

I can help you do things.

Tests referenced file detection with both valid and broken references in the body.

Does stuff.

Generates conventional commit messages from staged git diffs. Activates when the user requests a commit message and produces type(scope) subject format.

the frontmatter fence below is never closed

A conformant demo skill used as a conform pass fixture.

Partner skill.

A demo skill.

A demo skill.

Run a research → enrich → outreach SDR campaign from inside Claude Code, fully local with your own data-provider + model keys. This is the ORCHESTRATOR: it dispatches phase sub-agents (research, enrich, draft) in fixed order, checkpoints with you between…

Show which Intent Outreach data connectors are configured (have a bring-your-own key) versus skipped, with each one's tier. Use when the user asks which connectors or data providers are set up, whether a specific provider (apollo, hunter, …) is configured, or…

Inspect or scaffold an Intent Outreach Report Profile — the local file of deterministic knobs (intake, filtering, tone/length, output formats, delivery) that shape a campaign. Use when the user wants to list existing profiles, see a named profile, or create a…

Research one or more company domains (Intent Outreach Phase 1 only) — surface leads + contacts, with no enrichment or drafting. Use when the user wants quick account research, to find who works at a company, or to vet a domain list before committing to a full…

Saves a single fact, decision, pattern, or convention into the governed knowledge brain so it can be recalled later — and (for admins) retires memories that are outdated. Admin-only and side-effecting: it writes to the governed corpus, so it never auto-fires…

Answers questions about Intent Solutions' own systems, decisions, runbooks, and conventions from the governed knowledge brain, returning a qmd:// citation for every claim — receipts, not recall. Use when a teammate asks what the team knows about its own…

Runs an end-of-session capture sweep for the governed knowledge brain: reviews what happened, classifies insights, checks for conflicts, and proposes governed memories via the teamkb MCP tools. Admin capture workflow that complements the one-shot /brain-save.…

Read-only daily email check-in over Gmail or Outlook. Syncs the latest messages into the local store, then triages them (P1–P4 priority with a one-line "why", action-type, urgency signals, and detected deadlines), summarizes long threads, groups by category,…

Teach IntentMail your projects, clients, and priorities in plain language, then translate that context into concrete filing/priority rules. Reads a human-written context file (context/projects.md), and for filing or prioritization intent ("anything from Acme…

Take real inbox actions over Gmail or Outlook — mark read, archive, flag, move/relabel, draft replies, and (two-phase) delete — driven by triage. Safety-first: mutating operations preview a dry-run before executing, drafts are created but NEVER auto-sent,…

Analyzes DXF drawings deterministically — ADA/IBC code compliance, drawing health and QA, quantity takeoff, plain-English summaries, RFI generation, and room/zone detection — with no LLM or API key. Use when a user has a .dxf file and wants to check code…

Dog-food intentional-cognition-os against the operator's own system. Discovers a target — a folder of markdown docs, a project, or an ecosystem — creates an isolated ICO workspace outside the target tree, ingests and compiles its docs, runs a hand-authored…

Local-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds…