← Back to Skills Marketplace
gloria-zhang1

HerCycle

by gloria-zhang1 · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
356
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install hercycle
Description
Women's cycle intelligence companion. Reads Whoop biometric data (HRV, recovery, sleep, skin temperature) and menstrual cycle phase to understand which hormo...
README (SKILL.md)

HerCycle — Women's Cycle Intelligence

Built on the insight that women's biology is cyclical, not linear. Every month has four distinct hormonal seasons — each unlocking different cognitive, emotional, and physical capabilities. HerCycle reads your biometrics and tells you which season you're in, then takes action accordingly.

The Four Seasons

Season Phase Days What's Amplified
🌑 Winter Menstrual 1–5 Introspection, pattern recognition, deep insight, rest & recovery
🌱 Spring Follicular 6–14 Creativity, optimism, new ideas, social energy, starting things
☀️ Summer Ovulation ~14 Communication, charisma, negotiation, peak performance, visibility
🍂 Autumn Luteal 15–28 Detail orientation, completion, editing, boundaries, deep focus

Data Sources

HerCycle reads from:

  • Whoop API — HRV, recovery score, sleep quality, skin temperature (ovulation signal)
  • Cycle tracking — stored in WhoopClaw DB (cycle_tracking table), or inferred from skin temp patterns
  • Phase inference — if no explicit cycle log, estimate phase from skin temp trend + HRV patterns

See references/whoop-api.md for data access patterns.

Action Modules

Actions are pluggable. Each module takes the current phase + biometrics and returns a recommendation or triggers an action.

Current modules:

  • 🎵 Music — Spotify mood matching via a phase-aware playlist engine (see your WhoopClaw spotify_engine.py or bring your own)
  • 💪 Training — Push hard (follicular/ovulation) vs restore (menstrual/luteal)
  • 🥗 Nutrition — Iron-rich (menstrual), protein/carb cycling (luteal), light & fresh (ovulation)
  • 📅 Calendar — Phase-aware scheduling nudges (big meetings → ovulation, deep work → luteal)
  • 💬 Social — Energy level signal ("high charisma window" vs "protect your bandwidth")

To add a new action module: see references/action-modules.md.

Usage

Check current phase:

"What phase am I in?" / "What's my cycle season today?"

Phase-aware recommendation:

"Should I push hard at the gym today?" "What should I eat this week?" "Is this a good week for a big presentation?"

Trigger an action:

"Play music for my phase" / "Give me a playlist for my cycle phase"

Setup Requirements

HerCycle requires a running WhoopClaw instance — an open-source FastAPI backend that handles Whoop OAuth, cycle tracking, and biometric storage. Search GitHub for "WhoopClaw" to find an implementation, or build your own against the Whoop Developer API.

Prerequisites:

  1. Whoop API credentials — register at developer-dashboard.whoop.com to get your WHOOP_CLIENT_ID and WHOOP_CLIENT_SECRET
  2. WhoopClaw running locally — clone, configure .env, and start the server (uvicorn main:app)
  3. Whoop account connected — complete the OAuth flow via WhoopClaw's /whoop/authorize endpoint

Once running, configure WHOOPLAW_BASE_URL to point to your instance (default: http://localhost:8000).

Key endpoints HerCycle uses:

  • GET /whoop/recovery — latest recovery + HRV
  • GET /cycle/current-phase?telegram_id=\x3Cid> — current cycle phase
  • GET /cycle/predictions?telegram_id=\x3Cid> — next period prediction
  • GET /whoop/metrics/skin-temp — skin temperature trend (ovulation signal)

Always pull live data before making recommendations. Do not rely on stale cached values.

Philosophy

"Every month I experience four seasons... in this season, certain sensitivity and capacity is amplified." — Chloé Zhao, Oscar-winning director (BBC 100 Women)

The goal is not to manage around the cycle. It's to move with it — scheduling, eating, training, socialising, and creating in alignment with what's naturally amplified. The cycle is the intelligence. HerCycle makes it legible.

Usage Guidance
Do not install blindly. The SKILL.md requires a running WhoopClaw instance and Whoop API credentials (WHOOP_CLIENT_ID/SECRET) and implies additional integrations (Spotify, calendar, Telegram IDs) that are not declared in the registry metadata. Before installing: 1) confirm the skill's source and review WhoopClaw code you will point it at (running a third‑party backend on localhost can expose local services); 2) ensure any API keys you provide are minimal-scope and easily revocable; 3) verify which external tokens (Spotify, calendar) the skill will request and refuse to provide tokens you don't trust; 4) ask the publisher to correct metadata to list required env vars and to clarify endpoints and exact data flows; and 5) if you want to test, run WhoopClaw in an isolated/sandboxed environment and monitor network calls to confirm behavior. If the publisher cannot explain the missing credential declarations and endpoint inconsistencies, treat the skill as untrusted.
Capability Analysis
Type: OpenClaw Skill Name: hercycle Version: 1.0.0 The skill is classified as suspicious due to its reliance on a user-sourced, locally-run 'WhoopClaw' backend, which introduces a supply chain risk for the user. The `SKILL.md` and `references/whoop-api.md` files instruct the agent to make HTTP GET/POST requests to this local service (defaulting to `http://localhost:8000`), which, while intended for legitimate functionality, represents a network interaction with a potentially vulnerable or compromised component outside the skill bundle's direct control. There is no evidence of intentional malicious behavior such as data exfiltration to unauthorized external endpoints or backdoor installation.
Capability Assessment
Purpose & Capability
The skill claims to read Whoop biometrics via a local WhoopClaw backend and optionally trigger Spotify/calendar actions. Those capabilities legitimately require Whoop API credentials, a WhoopClaw base URL, and likely Spotify/calendar credentials — but the published metadata lists no required env vars/credentials. The declared purpose (Whoop-based cycle intelligence) aligns with the described endpoints, but the registry underreports needed capabilities and integrations (Spotify, calendar, possibly Telegram) which is incoherent.
Instruction Scope
SKILL.md instructs the agent to call local WhoopClaw endpoints (e.g., /whoop/recovery, /whoop/metrics/skin-temp, /cycle/current-phase) and to 'pull live data' before making recommendations. It also references reading a WhoopClaw DB table (`cycle_tracking`) and optional external modules (Spotify engine, calendar) — these broaden scope beyond a read-only recommendation interface. There are small inconsistencies in endpoint names across files (e.g., /cycle/current vs /cycle/current-phase) and unspecified use of identifiers (telegram_id) and triggers, leaving the agent broad latitude to access local network endpoints and external services.
Install Mechanism
No install spec and no code files: the skill is instruction-only, so it does not install packages or write files. This is lower risk from an installation standpoint, but increases reliance on runtime calls to local/external services described in the docs.
Credentials
The SKILL.md explicitly lists WHOOP_CLIENT_ID, WHOOP_CLIENT_SECRET and WHOOPLAW_BASE_URL as setup requirements (and implies Spotify/calendar credentials and identifiers like telegram_id), but the registry metadata declares no required env vars or primary credential. Underdeclaring required credentials is a red flag: it obfuscates which sensitive tokens the agent will need to access and transmit to local/external endpoints.
Persistence & Privilege
always:false (not force-included) and model invocation is allowed (default). Autonomous invocation is normal for skills; combined with the above concerns (local endpoint access, omitted creds), this increases potential exposure, but there is no indication the skill requests permanent system-level privileges or modifies other skills.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install hercycle
  3. After installation, invoke the skill by name or use /hercycle
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release. Women's cycle intelligence companion for Whoop — reads biometric data to identify hormonal phase and take phase-smart actions.
Metadata
Slug hercycle
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is HerCycle?

Women's cycle intelligence companion. Reads Whoop biometric data (HRV, recovery, sleep, skin temperature) and menstrual cycle phase to understand which hormo... It is an AI Agent Skill for Claude Code / OpenClaw, with 356 downloads so far.

How do I install HerCycle?

Run "/install hercycle" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is HerCycle free?

Yes, HerCycle is completely free (open-source). You can download, install and use it at no cost.

Which platforms does HerCycle support?

HerCycle is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created HerCycle?

It is built and maintained by gloria-zhang1 (@gloria-zhang1); the current version is v1.0.0.

💬 Comments