← Back to Skills Marketplace
crankaddict

Section 11: Endurance Training Coach (Intervals.icu)

by CrankAddict · GitHub ↗ · v1.0.13 · MIT-0
cross-platform ⚠ suspicious
2534
Downloads
5
Stars
0
Active Installs
15
Versions
Install in OpenClaw
/install section11
Description
Evidence-based endurance coaching protocol (v11.35). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning work...
Usage Guidance
This skill appears internally consistent for coaching: it reads local JSON training data and clearly points to the public Section‑11 GitHub repo for templates. Before installing or enabling it: (1) Confirm you are comfortable granting your platform access to any private repo you connect — that connector is how the skill would read private training files. (2) Review the SECTION_11.md and DOSSIER_TEMPLATE.md in the referenced GitHub repo to ensure no unexpected URLs or behavior are present. (3) Be aware the skill suggests saving templates and optionally adding a global 'data discipline' rule to your agent's system prompt — only do that if you want that global change. (4) Keep your training data in trusted locations and limit connector scopes (read-only) where possible.
Capability Analysis
Type: OpenClaw Skill Name: section11 Version: 1.0.13 The skill implements a dynamic instruction-loading pattern, fetching core coaching protocols and templates from a remote GitHub repository (CrankAddict/section-11) which are then interpreted as logic by the AI agent. This creates a supply-chain vulnerability where a compromise of the remote repository could lead to remote prompt injection. Additionally, the skill instructs the agent to modify its own persistent system configuration (SOUL.md) and references external write capabilities via 'push.py' for calendar management. While these features align with the stated coaching purpose, the remote fetching of executable instructions (SKILL.md, SECTION_11.md) is a high-risk design.
Capability Assessment
Purpose & Capability
Name/description (endurance coaching) matches the runtime instructions: read athlete JSON files, consult a dossier, apply the Section‑11 protocol, and generate reports/plans. Required artifacts (latest.json, history.json, intervals.json, routes.json, DOSSIER.md, HEARTBEAT.md) are exactly the kind of inputs expected for this purpose.
Instruction Scope
SKILL.md confines actions to reading local data, connected repo content (via platform connector), or specified raw GitHub URLs and saving templates into user data/workspace. It does not instruct the agent to read unrelated system files or to transmit user data to unknown endpoints. It does ask the agent to modify/save files in the agent workspace and to require that coaching numbers come from JSON reads, which is within scope for a coaching skill.
Install Mechanism
Instruction-only skill with no install spec and no code files. External fetches are to raw.githubusercontent.com (the public CrankAddict/section-11 repo), which is a standard release/source host. No archives or arbitrary downloads/exec are specified.
Credentials
The skill declares no required env vars or credentials. It does rely on platform-provided connectors (e.g., GitHub connector) and on the agent being allowed to read/write files in the user's data and workspace; these are expected for the functionality but are a privacy consideration because connecting a private repo or giving the agent workspace write access grants access to user data.
Persistence & Privilege
always:false and normal autonomous invocation. The SKILL.md asks the user to add a 'data discipline' rule to the agent's persistent configuration (system prompt / SOUL.md / custom instructions). That recommendation affects global agent behavior if applied; it's optional and user-driven, not an automatic modification by the skill itself.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install section11
  3. After installation, invoke the skill by name or use /section11
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.13
**Expanded data source support, tighter data discipline, and multi-platform improvements:** - Clarified data and template file locations for both local and cloud/connector setups, supporting agents (e.g., Claude, ChatGPT, Mistral). - New support for additional JSON sources: intervals.json, ftp_history.json, and routes.json for granular analysis (intervals, DFAs, terrain). - Enforced strict data discipline: every metric cited must come from a JSON read in the current response—no use of prior conversation, memory, or estimation. - Improved agent platform guidance, specifying expected behavior for GitHub connectors, direct file reads, and persistent configuration (SOUL.md, system prompts). - Updated protocol to version 11.35 and revised action hierarchy and fetch precedence for all required files and reports. - Refined first-use setup instructions and directory checks for a smoother onboarding experience.
v1.0.12
section11 v1.0.12 - Clarified that GitHub Actions write operations use repository secrets configured by the athlete. - Added explicit note that the heartbeat mechanism is fully opt-in and not enabled by default. - Clarified agent/repo access: Section 11 does not implement GitHub authentication and reads files only from locations already accessible by the runtime environment. - Minor wording improvements in security and automation sections for accuracy.
v1.0.11
Expanded write and calendar management capabilities, plus enhanced security and trust model documentation: - Added new write actions (list, move, delete, set-threshold, annotate) for managing workouts and data in Intervals.icu via push.py, all using a preview-then-confirm flow. - Clarified execution model: writes require explicit --confirm, and are only available on code-capable platforms (not web chat). - Expanded security and privacy section to explain layered trust boundaries, preview/write safety, and the repo-based supply-chain trust model. - Added guidance for users who wish to fork the protocol repository for stricter supply-chain control. - Updated documentation for all write-related features and references to push.py usage.
v1.0.10
- Added write capabilities: now supports pushing planned workouts to athlete calendars via push.py, when available. - Updated skill description to reflect protocol v11.10. - Clarified write support (workout planning) is only available on platforms that can execute code or trigger GitHub Actions. - Referenced template ID mappings and agentic workflow documentation for advanced write features. - No changes to coaching protocol, setup, or security practices.
v1.0.9
- Added a new "External Sources" section clarifying that all external files are maintained in the official CrankAddict/section-11 repository and can be inspected there. - Improved security & privacy documentation: now explicitly notes that the skill reads from user-configured JSON data, DOSSIER.md, and HEARTBEAT.md, and only writes DOSSIER.md/HEARTBEAT.md during first-use setup. - Clarified that data anonymization is handled solely by sync.py from the source repository; the skill itself does not perform anonymization. - No protocol or functional changes; documentation only.
v1.0.8
Version 1.0.8 - No code or logic changes; documentation only. - SKILL.md content has minor formatting updates but retains the previous protocol, actions, and privacy/security information. - There are no user-facing or operational changes in this release.
v1.0.7
Version 1.0.7 - Updated protocol version to 11.5. - First-use setup now mentions interactive guided setup using SETUP_ASSISTANT.md. - Clarified setup instructions to include the option for guided setup via AI chat. - No functional or structural changes to requirements or automation behavior.
v1.0.6
**Section 11 v1.0.6 changelog:** - Added initial `HEARTBEAT_TEMPLATE.md` file. - Updated protocol version to 11.4 with expanded data source and privacy/security instructions. - Now supports both `latest.json` (current snapshot) and `history.json` (longitudinal data) for training analysis. - Improved instructions for local and private GitHub repo setup. - Added detailed security, privacy, and network operation documentation to SKILL.md. - Adjusted required actions to include when to fetch each JSON data file.
v1.0.5
- Adds detailed first-use setup instructions including dossier, data source, and heartbeat configuration requirements. - Specifies new data hierarchy for coaching decisions. - Requires fetching athlete JSON data before responding to any training question. - Mandates use of standardized pre- and post-workout report templates. - Clarifies protocol adherence, validation, and heartbeat operation steps. - Emphasizes brevity in reports unless issues are detected or the athlete requests more detail.
v0.1.0
Initial release of section-11: evidence-based endurance cycling coaching protocol. - Provides protocol for handling athlete setup, including dossier, data source, and heartbeat configuration. - Specifies hierarchy and rules for data handling and analysis. - Requires always fetching athlete JSON training data before advising. - Outlines initial setup steps and protocol compliance for coaching scenarios. - Introduces heartbeat scheduling and observation workflow.
v1.0.4
- Added support for version 11.2 protocol, with updated version reference. - Expanded skill description to include pre/post-workout report generation. - Introduced required use of standardized report templates for pre- and post-workout analyses. - Clarified checklist use: now mandates Section 11 C validation before recommendations. - Added “brevity rule” to guide concise reporting when metrics are within normal thresholds. - No file changes; documentation update only.
v1.0.3
- Weekly heartbeat operation was updated to remove the requirement for "sports science review." - All other setup, protocol, data hierarchy, and required actions remain unchanged.
v1.0.2
Summary: Added heartbeat system for autonomous coaching operation. Changes: Added HEARTBEAT_TEMPLATE.md with configurable settings for location, timezone, weather thresholds, riding hours, and notification preferences Heartbeat configuration now required during first-use setup (alongside dossier and data source) Added HEARTBEAT.md to data hierarchy Added heartbeat operation section: daily training/weather checks, weekly analysis and sports science review, randomized self-scheduling
v1.0.1
Version: 1.0.1 Changelog: Added JSON data mirror setup instructions
v11.0.1
section11 11.0.1 changelog: - Initial release
Metadata
Slug section11
Version 1.0.13
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 15
Frequently Asked Questions

What is Section 11: Endurance Training Coach (Intervals.icu)?

Evidence-based endurance coaching protocol (v11.35). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning work... It is an AI Agent Skill for Claude Code / OpenClaw, with 2534 downloads so far.

How do I install Section 11: Endurance Training Coach (Intervals.icu)?

Run "/install section11" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Section 11: Endurance Training Coach (Intervals.icu) free?

Yes, Section 11: Endurance Training Coach (Intervals.icu) is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Section 11: Endurance Training Coach (Intervals.icu) support?

Section 11: Endurance Training Coach (Intervals.icu) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Section 11: Endurance Training Coach (Intervals.icu)?

It is built and maintained by CrankAddict (@crankaddict); the current version is v1.0.13.

💬 Comments