Sherpa-B Reference

Gym UI

Sherpa-B Gym UI: the logged-in dashboard that provides an observability layer for tasks and progress tracking. UI provides limited interactivity because most of the functionality is controlled via the MCP Server.

MCP Server

Sherpa-B MCP Server: tools providing contextual guidance for the tasks involved in taking an agentic application from idea to monetization, ranging from freestyle tasks to guided planning and execution workouts..

Plugin

Sherpa-B Plugin: a customization layer over the Sherpa-B MCP server's tools, wrapping them as agent skills exposed via slash commands or packaged into orchestrated multi-step workflows.

Telemetry

Local telemetry buffer/sync client for the sherpa-b Claude Code plugin

shb-track-event

Append a validated telemetry event to the local buffer file.

shb-read-log

Read local `log_entry` telemetry events for display to the LLM mid-workout.

shb-check-update

Upgrade the installed shb_telemetry only when a newer version is bundled

Slash Commands

Every slash command available in the Sherpa-B Claude Code plugin, generated directly from the plugin's skill definitions. Each command runs a guided workout from the Sherpa-B MCP server. This list always matches the commands actually shipped in the plugin.

Utilities

/architecture

transform your LLM call inventory into a clean agent architecture with clear boundaries, control loops, and handoff contracts

/audit-code-to-specs

compare your codebase against its specifications to identify gaps and drift, then create GitHub issues for everything that needs attention

/begin-work

select the right issue to work on, create a branch, write tests first, and implement the solution

/bonus_talk_to_investors

decide whether you should raise at all, then walk into any investor conversation with a default alive position, an evidence-based traction narrative, a specific ask, and a walk-away number

/build_form_check

walk through your first agentic-engineering build cycle by creating three real tools, then review your existing code with fresh eyes

/context_management

design how information flows through your LLM calls, ensuring each reasoning step gets exactly what it needs while avoiding context bloat and quality risks

/cool-down

close out a session outside any workout - commit changes, reflect, persist notable decisions/facts/preferences, and recap what got logged

/create_social_post

turn a workout reflection, planning doc, or general observation into a ready-to-publish social post in the participant's own voice

/create-issues

capture, structure, and create GitHub issues from conversations, code reviews, or feature ideas so nothing gets lost

/demoing_your_agent

build a compelling 8-minute demo narrative that resonates with your target audience - craft your story arc, storyboard your visuals, develop your script, and prepare for recording

/evaluation_at_scale

transform your agent architecture into a diagnostic evaluation system by validating context inputs structurally, evaluating outputs semantically, and tracing failures back to context management issues

/evaluation_dataset

design systematic evaluation for your AI agent through risk-driven test case creation

/finish-work

finalize your PR with spec updates, follow-up issues, and code cleanup, then mark it ready for review

/first_deployment

deploy your agent to a small group of testers to validate your quality risk assumptions through real-world usage

/ideation

identify automation opportunities and design semi-autonomous AI agents

/implementation

design the delivery mechanism for your agent and translate your workout into a working implementation with minimal scope

/manage-tasks

Long-lived work coordinator - surface Sherpa-B tasks and this repo's GitHub issues together, help decide what's next, hand off the actual work to a second terminal, and verify it really got done before looping

/open-dashboard

Get a short-lived link to open the Sherpa-B web dashboard in a browser, optionally to a specific page

/orientation

First-time onboarding for bootcamp participants - sets up workspace and gets to know them

/persist-content

Persist notable info from this session to telemetry/prose docs, ad hoc - not tied to a workout checkpoint

/project-init

Bind this repo to a Sherpa-B project by running init with a real git identity

/review-my-code

review your own code changes with quality checks before requesting peer review

/shb-doctor

Check that orientation's plugin setup (telemetry install, seeds, settings) is actually in place, and fix anything missing

/sparring_session

rehearse defending your codebase against a roleplayed skeptical persona (customer, CTO, investor, employer, or others) before a presentation, surfacing blind spots while it's still safe to find them

/sprint_demo_prep

prepare to record a 4-5 minute sprint demo video - verify the app works, draft a timed script, sketch diagrams, and get recording-ready

/user_experience

design your agent's user experience by mapping how user context flows into agent context and creating implementation-ready UX specifications

/user_research

find and talk to real users, learning directly about their needs, current solutions, and biggest pain points

/w1_positioning_workshop

lock down what you are, for whom, and against what alternative - a positioning statement and one-page brief that governs every downstream GTM decision

/w10_pmf_signal_dashboard

read whether your business has product-market fit by scoring five hard signals - retention shape, the 40% test, organic vs. pushed growth, revenue quality, and default alive - then write the pivot trigger before emotion enters the room

/w2_cash_capital_strategy

establish your real financial position - runway, unit economics, deal size floor, cash flow architecture, and funding path - before making any GTM decision

/w3_icp_hypothesis_canvas

turn a vague sense of "who our customer is" into a falsifiable first-customer hypothesis - job-to-be-done, cost and frequency of the problem, buyer authority, trigger - specific enough to name 10 real people and test it in three conversations

/w4_unscalable_acquisition_playbook

manually acquire your first customers before automating anything - map your existing access, rank targets by pain x reachability, write ten personalized messages, run the sprint, and extract the patterns that decide whether you are ready to systematize

/w5_outreach_engine_builder

turn the manual outreach signal from your unscalable acquisition sprint into a repeatable engine - ICP signal card, message architecture, cadence map, volume model, and a minimal tooling stack you can operate alone

/w6_discovery_call_framework

prepare for a specific upcoming customer conversation, drill Mom Test question discipline, and convert the call into a dollar-quantified pain statement, gap map, and qualification verdict

/w7_objection_navigation_closing

turn sales pushback into a classified objection map, non-collapsing response scripts, and a closing sequence that ends in a named commitment

/w8_pricing_experiment_framework

set a first price you can defend with logic - anchored to discovered customer value, structured before it is numbered, and designed as a market experiment with pass/fail signals rather than a permanent commitment

/w9_pilot_to_arr_playbook

design the pilot before it starts - conversion path, customer-owned success metrics, a defensible opt-out clause, cash-flow-safe payment terms, and an expansion motion wired into the agreement

/warm-up

start a session by reviewing recently logged telemetry - kind/domain/risk_dimension/actor-role stats - and let the participant correct anything stale or wrong before diving in