The skill had mtb-xco-demands.md but road/TT demands were only diffused
through the general docs — an asymmetry given the balanced MTB+road scope.
Add two dedicated, self-contained demand profiles (kept separate because
mass-start racing and TT differ as much as XCO differs from marathon MTB):
- references/road-racing-demands.md: stochastic power profile (Vogt 2007,
Ebert 2005/2006, Sanders/van Erp 2021), drafting economics (Blocken 2018),
fatigued finishing sprint (Menaspà 2013/2015, Etxebarria 2019), durability
as a success determinant (van Erp/Sanders/Lamberts 2021); power governs, HR
unreliable (intermittent) — mirrors the MTB doc.
- references/tt-demands.md: aero drag dominance + CdA as the top lever
(Crouch 2017, Martin 1998, García-López 2008), critical power as predictor
(Smith 1999), even-vs-variable pacing (Swain 1997, Atkinson 2007), long-TT
durability (Maunder 2021); HR more usable than MTB but still secondary.
All new quantitative claims carry verified PMIDs/DOIs (verified via PubMed/
CrossRef); citations.md gains Road-racing and Time-trial sections. Honesty
flags: Blocken 2018 and Martin 1998 have no PMID (DOI only); the '~90% aero'
soundbite (Kyle & Burke 1984) is unverifiable and marked approximate;
criterium-specific literature flagged as a gap; no unverified HR-reliability
citation added (TT HR defers to data-confounds.md).
Router (SKILL.md) and README layout updated with both docs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TqrhBhC3GEcKyaw8RTk8G6
Review of the VO2 conflict section against primary sources (verified via
PubMed + search):
- Rønnestad & Hansen 2016 (PMID 23942167) confirmed: 13 cyclists, 30s vs
50%/80% Tmax at 2:1 work:rest, measured time >=90% VO2peak, 30s won. Table
row corrected to reflect the actual comparison.
- Yang 2025 optimum ~140s is a MEDIUM rep (~2.3 min), between the poles.
Section reframed from binary short-vs-long to an inverted-U with a
modality/protocol-dependent peak. 'Weighted toward running' softened to
match what the abstract actually supports.
- Removed the overstatement 'best-controlled evidence favors short 30/15
intervals'. Added two caveats: (1) cycling short-interval superiority is
largely one research group; (2) effort-matched work (total-work-matched)
reportedly nulls the advantage (Seiler group; unpublished/secondary,
flagged low-tier, not cited as fact).
- Practical menu now defaults to medium (~2-4 min, near the pooled optimum)
rather than short; short/long presented as goal-dependent options.
- citations.md: added single-group caveat on Ronnestad body of work and an
explicit NOT-VERIFIABLE entry for the effort-matched replication.
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