New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Glycemicgpt Mock Service

by lumose-health in lumose-health/GlycemicGPT

Understand and safely modify the GlycemicGPT development only MSW web mock API.

GPL-3.0Auto-check passedDevelopment

Install Glycemicgpt Mock Service

skills CLI
$ npx skills add lumose-health/GlycemicGPT --skill glycemicgpt-mock-service -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lumose-health/GlycemicGPT glycemicgpt-mock-service --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lumose-health/GlycemicGPT.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/glycemicgpt-mock-service .claude/skills/glycemicgpt-mock-service && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
glycemicgpt-mock-service
GitHub stars
141
Token cost
~1.8k tokens
SKILL.md length
928 words
Files
2
Skills in repo
3
Repo updated
First seen
Licence
GPL-3.0

At a glance

Understand and safely modify the GlycemicGPT development only MSW web mock API.

  • Works in 4 steps: For activation and production… → For scenarios and developer controls,… → For request behavior, find the endpoint… → …
  • Adding endpoints to
  • SKILL.md covers Read Before Acting, Understand the Runtime, Change Workflow and Testing Workflow, plus 1 more section
  • Calls npm

What it does

Glycemicgpt Mock Service is an agent skill from lumose-health/GlycemicGPT. Understand and safely modify the GlycemicGPT development only MSW web mock API. Use when investigating, debugging, testing, documenting, adding endpoints to, or changing mock data, scenarios, runtime activation, request handlers, generated responses, the development control panel, or the mock service worker in apps/web.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development. The repository describes itself as: Because no one should manage diabetes alone 💙. The licence is GPL-3.0.

When your agent uses it

  • Adding endpoints to
  • Changing mock data
  • Runtime activation
  • Request handlers

Example prompts

  • “/glycemicgpt-mock-service”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. For activation and production boundaries, read apps/web/src/middleware.ts, apps/web/src/app/layout.tsx, apps/web/src/mocks/server.ts…
  2. For scenarios and developer controls, read apps/web/src/mocks/types.ts, apps/web/src/mocks/state.ts, and…
  3. For request behavior, find the endpoint in apps/web/src/mocks/handlers.ts, then inspect the response builder in apps/web/src/mocks/data.ts…
  4. For tests, read the colocated mock tests plus apps/web/tests/middleware.test.ts when activation is relevant.

What it can do on your machine

Read from SKILL.md and the folder at commit d1a9adb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Glycemicgpt Mock Service loads about 1.8k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 928 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lumose-health/GlycemicGPT at commit d1a9adb, republished under its GPL-3.0 licence (© lumose-health). 928 words, ~1,810 tokens.

Download SKILL.mdSave it as .claude/skills/glycemicgpt-mock-service/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
glycemicgpt-mock-service
description
Understand and safely modify the GlycemicGPT development only MSW web mock API. Use when investigating, debugging, testing, documenting, adding endpoints to, or changing mock data, scenarios, runtime activation, request handlers, generated responses, the development control panel, or the mock service worker in apps/web.

GlycemicGPT Mock Service

Use the repository implementation and API contracts as the source of truth. Do not rely on generic MSW assumptions when the local design answers the question.

Read Before Acting

Always read:

  1. docs/dev/mock-data-service.md

If a repository-local AGENTS.md exists, follow its applicable instructions. Do not require it because fresh clones do not include that gitignored file.

Then load only the source needed for the task:

  1. For activation and production boundaries, read apps/web/src/middleware.ts, apps/web/src/app/layout.tsx, apps/web/src/mocks/server.ts, apps/web/src/mocks/MockProvider.tsx, apps/web/src/mocks/browser.ts, and apps/web/Dockerfile.
  2. For scenarios and developer controls, read apps/web/src/mocks/types.ts, apps/web/src/mocks/state.ts, and apps/web/src/mocks/DevMockPanel.tsx.
  3. For request behavior, find the endpoint in apps/web/src/mocks/handlers.ts, then inspect the response builder in apps/web/src/mocks/data.ts and the real API client or contract used by the calling feature.
  4. For tests, read the colocated mock tests plus apps/web/__tests__/middleware.test.ts when activation is relevant.

Use rg to locate an endpoint or builder before reading the large handler and data files in full.

Understand the Runtime

Activation is request scoped at first render:

  1. A browser sends x-glycemicgpt-mock-api: 1 on the initial request.
  2. Middleware honors it only when NODE_ENV is development. It also treats the request as authenticated for protected dashboard routes and forwards the header.
  3. The root layout reads the header and passes the result to MockProvider.
  4. The provider waits for startMockWorker() before rendering the application. Worker startup is memoized, failed starts can retry, and the panel reports failure as MSW inactive.
  5. The worker intercepts normal /api/* calls in the browser. No product component should need mock specific branches.

Request handling follows this path:

  1. handlers.ts reads request parameters and the current runtime state.
  2. It obtains a generated snapshot cached by serialized state and a five minute time bucket.
  3. Builders in data.ts return deterministic glucose, pump, integration, alert, insight, brief, and settings payloads.
  4. Explicit handlers return the same response shapes and status codes expected from the real API.
  5. The final catch all handler returns 501 for any uncovered /api/* route. Handler order is therefore part of the contract.

Baseline generated data is deterministic but intentionally varied. A seven day cycle includes one brief urgent low excursion and one brief urgent high excursion. Automated basal delivery follows a scheduled profile, then responds to glucose, activity mode, and seeded daily variation. Predicted low suspensions occur with the periodic low excursion rather than every day.

Glucose history, stats, and time in range builders share the same selected window filter. Only history responses apply the default pagination limit. Aggregate endpoints must use every filtered reading unless the request explicitly supplies a limit, otherwise dashboard summaries drift from the glucose trend chart.

Runtime state follows these rules:

  1. types.ts defines all valid sources, events, limits, and defaults.
  2. state.ts normalizes every stored value and persists browser state under glycemicgpt:mock-runtime.
  3. Browser state writes dispatch glycemicgpt:mock-state-change and update updatedAt, which also invalidates the snapshot cache key.
  4. Node based handler tests use the in memory state fallback because localStorage is unavailable.
  5. Generated daily briefs and insight responses use their own browser storage keys in data.ts.
  6. Scenario controls persist on selection. MockProvider subscribes to state changes and remounts application content so normal API hooks refetch without a browser reload. Backfill days keep an explicit action because the numeric input must be complete before applying it.

Production has two defenses. Development modules are loaded only behind NODE_ENV === "development", and the production image removes public/mockServiceWorker.js.

Show full SKILL.md (362 more words)Show less

Change Workflow

  1. Trace the real frontend request and its TypeScript contract. Inspect the backend route when the contract or status behavior is unclear.
  2. Decide the correct ownership layer. Put deterministic construction and derived calculations in data.ts. Put HTTP parsing, response status, and endpoint side effects in handlers.ts.
  3. Reuse existing builders where possible. Keep dates, limits, units, source identifiers, and empty states consistent across related endpoints.
  4. Add the explicit handler before the final guard. Never weaken the guard or allow an unmatched API call to reach a real backend.
  5. Add runtime state only for behavior that developers must control across requests. Update MockRuntimeState, defaults, normalization, options, panel controls when applicable, and state tests together.
  6. Write mutations through setMockRuntimeState. Do not mutate the cached snapshot or browser storage directly from a handler.
  7. Keep the application mock agnostic. Do not import src/mocks from normal feature components or replace API clients with mock specific code.
  8. Update docs/dev/mock-data-service.md when activation, architecture, ownership, safety boundaries, or the contributor workflow changes.

Testing Workflow

Add direct behavioral tests at the changed boundary:

  1. Test pure generation and derived responses in apps/web/src/mocks/data.test.ts with a fixed date and explicit state.
  2. Test normalization, persistence, limits, and subscriptions in apps/web/src/mocks/state.test.ts.
  3. Test endpoints through MSW's public setupServer(...handlers) and fetch flow in apps/web/src/mocks/handlers.test.ts. Do not test handler source text or private MSW APIs.
  4. Test worker startup and failure states in apps/web/src/mocks/MockProvider.test.tsx.
  5. Test request gating, auth bypass, and header forwarding in apps/web/__tests__/middleware.test.ts.

Run focused tests while iterating. Before completion, run from apps/web:

sh
npm test
npm run typecheck
npm run build

For runtime or control changes, reuse the app on port 3003, enable the request header before loading the dashboard, confirm the panel says MSW active, exercise the changed scenario, and inspect the intercepted response. Do not start a second web server on another port.

Critical Rules

  1. Keep mock mode opt in, browser side, and development only.
  2. Never seed a real backend or send fake data to a real API.
  3. Keep production components on real API contracts.
  4. Keep the 501 API guard last.
  5. Preserve deterministic output for fixed state and time.
  6. Verify behavior through requests, not implementation text.

© lumose-health, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/glycemicgpt-mock-service of lumose-health/GlycemicGPT.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit d1a9adb

Compare with similar skills

Glycemicgpt Mock Service next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Glycemicgpt Mock Service compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Glycemicgpt Mock Service this skilllumose-health/GlycemicGPT141—~1.8kAutomated safety check: PassGPL-3.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from lumose-health/GlycemicGPT

  • LLM Benchmark

    lumose-health/GlycemicGPT

    A skill your agent uses when the user wants to benchmark, evaluate, or vet an LLM/AI model for GlycemicGPT — checks a configured model for safety/correctness and performance against the project's…

    141 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed

  • Glycemicgpt UI Foundation

    lumose-health/GlycemicGPT

    A skill your agent uses when adding or changing GlycemicGPT web UI structure, shared styling, Tailwind classes, semantic theme tokens, typography, base primitives, product UI components, TextInput…

    141 GitHub stars~707 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Glycemicgpt Mock Service

What does Glycemicgpt Mock Service do?

Understand and safely modify the GlycemicGPT development only MSW web mock API. Glycemicgpt Mock Service is an agent skill from lumose-health/GlycemicGPT. Understand and safely modify the GlycemicGPT development only MSW web mock API.

When should I use Glycemicgpt Mock Service?

Glycemicgpt Mock Service fits situations like: adding endpoints to; changing mock data; runtime activation; request handlers.

How do I install Glycemicgpt Mock Service in Claude Code?

Run `npx skills add lumose-health/GlycemicGPT --skill glycemicgpt-mock-service -a claude-code`. Or copy the skill folder (.agents/skills/glycemicgpt-mock-service in lumose-health/GlycemicGPT) into .claude/skills/glycemicgpt-mock-service in your project. Claude Code loads it when a task matches its description.

How do I install Glycemicgpt Mock Service in Codex?

Run `npx skills add lumose-health/GlycemicGPT --skill glycemicgpt-mock-service -a codex`. Or copy the skill folder (.agents/skills/glycemicgpt-mock-service in lumose-health/GlycemicGPT) into .agents/skills/glycemicgpt-mock-service in your project. Codex loads it when a task matches its description.

Can I use Glycemicgpt Mock Service in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lumose-health/GlycemicGPT --skill glycemicgpt-mock-service -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/glycemicgpt-mock-service, .gemini/skills/glycemicgpt-mock-service, .github/skills/glycemicgpt-mock-service and .opencode/skills/glycemicgpt-mock-service in your project.

What does Glycemicgpt Mock Service need to run?

Going by SKILL.md and its folder, Glycemicgpt Mock Service needs the command-line tools its instructions call (npm).

Does Glycemicgpt Mock Service access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Glycemicgpt Mock Service safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Glycemicgpt Mock Service use?

Glycemicgpt Mock Service is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Glycemicgpt Mock Service use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Glycemicgpt Mock Service?

Skills that share tags, products or a category with Glycemicgpt Mock Service: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Glycemicgpt Mock Service?

lumose-health (a GitHub organization) maintains it in lumose-health/GlycemicGPT, which has 141 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 8, 2026.

Source: lumose-health/GlycemicGPT on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.