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,…

Analyze real sMAPE and MASE results produced by the community Nixtla Baseline Lab, compare models, and surface fragile series without inventing benchmarks. Use when reviewing StatsForecast output; trigger with "baseline review", "interpret sMAPE/MASE", or…

Audit, debug, and improve Agent Skills without conflating the portable base format with repository-specific marketplace rules. Use when creating or repairing SKILL.md packages; trigger with "skill not loading", "frontmatter", "allowed-tools", or "validate…

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…

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…

Analyzes verified SearchCarriers evidence for carrier integration operator. Use when a user asks, "Health-check the API and prepare a resumable…". Trigger with "Health-check the API and prepare a…".

Analyzes verified SearchCarriers evidence for carrier intel mcp operator. Use when a user asks, "Use Carrier Intel to source van carriers on an…". Trigger with "Use Carrier Intel to source van…".

Analyzes carrier evidence for carrier decision report builder. Use when a user asks, "Build an audit-ready vetting report from these tool…". Trigger with "Build an audit-ready vetting…".

Analyzes verified SearchCarriers evidence for risk engine mcp operator. Use when a user asks, "Run the Risk Engine with our supplied carrier…". Trigger with "Run the Risk Engine with our…".

Analyzes carrier evidence for carrier watch operations. Use when a user asks, "Watch DOT 1234567 for details and inspections, then…". Trigger with "Watch DOT 1234567 for details and…".

Analyzes carrier evidence for resumable carrier batch runner. Use when a user asks, "Refresh our 500-carrier panel and make the run…". Trigger with "Refresh our 500-carrier panel and…".

Analyzes carrier evidence for trusted contact consistency check. Use when a user asks, "The rate confirmation came from a new email;…". Trigger with "The rate confirmation came from a…".

Analyzes carrier evidence for auditable carrier exporter. Use when a user asks, "Export our approved carrier panel to formula-safe…". Trigger with "Export our approved carrier panel…".

Manage API health, run bulk carrier lookups, sync TMS data, and configure webhooks. Use when scaling carrier operations.

Interprets carrier data from the carrier-intel MCP tools and provides freight industry context. Use when processing carrier lookup results.

Generate vetting reports, fleet analysis, comparisons, and data exports. Use when producing carrier documentation or formatted output.

Assess carrier risk with scoring, vetting, insurance, and compliance tools. Use when evaluating carrier safety or qualification.

Manage SearchCarriers company watches, format supplied notifications, and run point-in-time compliance checks. Use when operating carrier monitoring.

Batch processes carrier lookups from CSV or DOT lists with rate limiting and progress reporting. Use when bulk looking up or mass vetting carriers.

Validates carrier contact info including phones, addresses, and emails. Use when verifying contact quality or detecting shared contacts.

Exports carrier data as CSV, JSON, markdown, or comparison tables with configurable fields. Use when exporting or formatting carrier data.

Generate deterministic prototype hypotheses, simulated experiment findings, and aggregate confidence summaries. Use when exercising an offline research-loop contract, not when collecting real evidence. Trigger with research prototype.

Simulate browser navigation metadata, selector extraction, and screenshot paths without network or file writes. Use when testing the Browser AI contract offline. Trigger with simulate browser or browser contract.

Exercise an offline prototype that returns synthetic research findings, code stubs, and packaged artifact dictionaries. Use when testing a Deer Flow-shaped pipeline contract. Trigger with prototype research and code.

Simulate element detection, UI actions, and form-validation results without opening a browser or changing a page. Use when exercising the GUI Agent contract offline. Trigger with simulate GUI or page-agent prototype.

Generate synthetic graph counts, ranked artificial entities, and relationship paths from input strings. Use when testing the Knowledge Graph response contract, not when analyzing real source code. Trigger with simulate knowledge graph.

Score supplied text with deterministic keyword heuristics for sentiment, stance, and bias. Use when testing explainable offline classification behavior, not for population-level opinion claims. Trigger with analyze text heuristically.

Estimate a repository score from its owner/name string and optionally scaffold a local specialist directory. Use when exercising OSS Agent Lab's offline repo intake prototype. Trigger with scan repo prototype.

Validate snippets with local keyword rules and return simulated execution output without running code. Use when testing the Sandbox response contract safely. Trigger with validate snippet or simulate execution.

Every marketplace field is present but three are the wrong shape for the kernel contract.

Carries every marketplace field except version; the conform floor passes it, the marketplace tier must not.

A demo skill carrying the full IS marketplace frontmatter set, used as the conform --tier marketplace pass fixture.

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.

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

Evaluate an Agent Skill with JRig and return an evidence-backed ship, warn, block, or obsolete-review decision. Use when grading, scoring, release-gating, regression-testing, or comparing a SKILL.md before publication. Trigger with "evaluate this skill",…

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.

Normalize supplied X post objects, redact common sensitive strings, score heuristic signals, deduplicate similar text, and persist deterministic bug clusters with the repository's Bun libraries. Use when developing or testing the local clustering stage.…

Exercise the triage server's five owner-lookup contracts and produce an explicit uncertainty result when the current prototype returns no team. Use when testing routing precedence or documenting missing ownership data. Trigger with "route this bug cluster".

Exercise the triage server's synthetic repository-evidence contracts and label every result as unverified prototype output. Use when testing evidence schemas, tier assignment, or downstream display behavior without GitHub. Trigger with "simulate a repo scan…

Format supplied cluster data as bounded terminal Markdown and parse one review-command string with the triage MCP parser. Use when previewing triage output or validating command syntax without mutating cluster state. Trigger with "format this triage summary"…

Analyze bounded public X data through the live intake tools, then exercise the repository's local heuristic, synthetic evidence, routing, draft, and command contracts with explicit prototype labels. Use when evaluating this triage system or collecting an…

Manage Slack channel access control — pairing, allowlist, channel opt-in. Use when approving a pairing code, changing the DM policy, editing the user allowlist, or opting a channel in or out. Trigger with "/slack-channel:access", "pair my slack account", "add…

Configure Slack channel tokens (bot token + app-level token). Use when writing or rotating the Slack bot and app-level tokens for the slack-channel plugin. Trigger with "/slack-channel:configure", "configure slack tokens", or "set up my slack bot token".

Detect installation failures and install, verify, repair, reset, or uninstall the CCSC Slack channel. Use when setting up the Slack channel, checking an existing installation, exporting its Slack app manifest, or safely tearing it down. Trigger with…

Analyze and author MCP tool-call policy rules without hand-editing access.json. Use when adding, linting, or removing auto_approve/deny/require_approval rules for the Slack channel's policy engine. Trigger with "/slack-channel:policy", "add a policy rule",…

Run a local research, enrichment, and outreach-drafting workflow over company domains with bring-your-own provider keys. Use when a user wants a reviewed SDR campaign or grounded cold-email drafts. Trigger with "run an outreach campaign", "prospect these…

Inspect the bundled Intent Outreach connector registry without running research or enrichment. Use when a user asks which providers are configured or wants a campaign preflight. Trigger with "/outreach-connectors", "connector status", or "which data providers…

List, inspect, or scaffold a local Intent Outreach Report Profile JSON file. Use when a user wants to manage repeatable campaign settings while preserving existing files. Trigger with "/outreach-profile", "show my outreach profile", or "create an outreach…

Research company domains through configured Intent Outreach connectors without enriching or drafting. Use when a user wants a grounded lead/contact discovery pass before a campaign. Trigger with "/outreach-research", "research these domains", or "find…

Create one Registrar memory proposal or apply a supported lifecycle transition to an existing memory. This is a local operator write and never auto-fires. Use when an administrator needs to preserve one team fact or retire an outdated memory. Trigger with…

Search and analyze Intent Solutions' governed team memory through the Registrar, returning qmd:// citations for supported claims. Use when checking recorded architecture, infrastructure, decisions, runbooks, or conventions. Trigger with "/brain", "ask the…

Review, classify, and capture a bounded set of team insights or explicitly approved Markdown files through the local Registrar operator tools. This is side-effecting and never auto-fires. Use when closing a session, importing a small document batch, reviewing…