Tighten the router so race-specific reasoning in the general docs points to
the matching demand profile instead of speaking in a road/TT-default voice:
- periodization.md: anchor the build phase's 'race-specific top-end' to the
matching demand doc (tt / road-racing / mtb-xco).
- durability.md: show how fatigue resistance manifests per discipline.
- data-confounds.md: extend the intermittent-HR caveat to road racing/crits;
note TT as the steadier exception where HR is more usable.
- strength-for-cyclists.md: link the explosive/sprint transfer to road-racing
and sustained-power transfer to TT.
- vo2max-intervals.md: match rep length to event (short=surges/road+MTB,
long=sustained/TT); extend the HR caveat to road racing.
All internal links verified resolving.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TqrhBhC3GEcKyaw8RTk8G6
Modular cycling-training skill: periodization logic, workout design, and
research-backed protocols that companion an Intervals.icu MCP server (the
server owns all data + computed metrics; the skill owns knowledge + reasoning).
Structure:
- SKILL.md router + README (companion-to-MCP architecture, install steps)
- references/: durability, mtb-xco-demands, strength-for-cyclists,
vo2max-intervals, periodization, data-confounds, citations
- assets/: base + build plan templates, durability field-test protocol
Every quantitative claim carries an inline citation; citations.md is the
single source of truth with PMID/DOI, each verified against PubMed on
2026-07-20. Notable honesty flags baked in:
- VO2 rep-length: running (Fleckenstein 2025) vs cycling (Ronnestad) conflict
documented rather than asserted; cycling evidence favors short intervals.
- 'Yu et al. 2025' (frequency > distribution) could not be found; not cited.
- Under-researched doses (durability, taper TSB, CTL ramp) flagged 'track response'.
- HR-confound doc forbids naive decoupling<5% / RHR+5 rules.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TqrhBhC3GEcKyaw8RTk8G6
Chris Farhood