feat: add road-racing and TT demand docs (balance the MTB doc)

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

references/citations.md

@@ -80,6 +80,98 @@ Fransen J, Dascombe BJ. *Predictors of performance in a 4-h mountain-bike race.*
 
 ---
 
+## Road-racing demands (mass-start / criterium)
+
+**✅ Vogt et al. 2007** — TdF mass-start mean power only ~3.1–3.3 W/kg (218–234 W) despite decisive
+higher efforts; stochastic profile. Vogt S, Schumacher YO, Roecker K, Dickhuth H-H, Schoberer U,
+Schmid A, Heinrich L. *Power Output during the Tour de France.* Int J Sports Med. 2007;28(9):
+756–761. **PMID 17497569 · DOI 10.1055/s-2007-964982.**
+
+**✅ Ebert et al. 2006** — pro men's tour: low mean power with repeated surges above maximal aerobic
+power. Ebert TR, Martin DT, Stephens B, Withers RT. *Power output during a professional men's
+road-cycling tour.* Int J Sports Physiol Perform. 2006;1(4):324–335. **PMID 19124890 ·
+DOI 10.1123/ijspp.1.4.324.**
+
+**✅ Ebert et al. 2005** — women's World Cup power-output profile (SRM). Ebert TR, Martin DT,
+McDonald W, Victor J, Plummer J, Withers RT. *Power output during women's World Cup road cycle
+racing.* Eur J Appl Physiol. 2005;95(5–6):529–536. **PMID 16151832 · DOI 10.1007/s00421-005-0039-y.**
+
+**✅ Sanders & van Erp 2021** — updated review: demands strongly shaped by stage/race type. Sanders
+D, van Erp T. *The Physical Demands and Power Profile of Professional Men's Cycling Races: An Updated
+Review.* Int J Sports Physiol Perform. 2021;16(1):3–12. **PMID 33271501 · DOI 10.1123/ijspp.2020-0508.**
+
+**✅ van Erp & Sanders 2021** — 2,920 files / 20 pros: demands vary by race category and result.
+van Erp T, Sanders D. *Demands of professional cycling races: Influence of race category and result.*
+Eur J Sport Sci. 2021;21(5):666–677. **PMID 32584197 · DOI 10.1080/17461391.2020.1788651.**
+
+**✅ Blocken et al. 2018** — CFD + wind tunnel: peloton drag drops to ~5–10% of an isolated rider.
+**No PMID — cite by DOI** (journal not MEDLINE-indexed). Blocken B, van Druenen T, Toparlar Y,
+Malizia F, Mannion P, Andrianne T, Marchal T, Maas G-J, Diepens J. *Aerodynamic drag in cycling
+pelotons: New insights by CFD simulation and wind tunnel testing.* J Wind Eng Ind Aerodyn.
+2018;179:319–337. **DOI 10.1016/j.jweia.2018.06.011.**
+
+**✅ Menaspà et al. 2015** — pro road sprint peak ~17.4 ± 1.7 W/kg, preceded by high-intensity
+lead-in. Menaspà P, Quod M, Martin DT, Peiffer JJ, Abbiss CR. *Physical Demands of Sprinting in
+Professional Road Cycling.* Int J Sports Med. 2015;36(13):1058–1062. **PMID 26252551 ·
+DOI 10.1055/s-0035-1554697.**
+
+**✅ Menaspà, Abbiss & Martin 2013** — world-class sprinter Grand Tour performance analysis.
+Menaspà P, Abbiss CR, Martin DT. *Performance analysis of a world-class sprinter during cycling
+grand tours.* Int J Sports Physiol Perform. 2013;8(3):336–340. **PMID 23038704 ·
+DOI 10.1123/ijspp.8.3.336.**
+
+**✅ van Erp, Sanders & Lamberts 2021** — maintaining maximal power after high accumulated work is a
+key success determinant (durability in road racing). van Erp T, Sanders D, Lamberts RP. *Maintaining
+Power Output with Accumulating Levels of Work Done Is a Key Determinant for Success in Professional
+Cycling.* Med Sci Sports Exerc. 2021;53(9):1903–1910. **PMID 33731651 ·
+DOI 10.1249/MSS.0000000000002656.**
+
+**✅ Etxebarria et al. 2019** — ~1 h prior stochastic cycling cut a subsequent 30 s sprint ~5–6%
+(criterium/finish relevance). Etxebarria N, Ingham SA, Ferguson RA, Bentley DJ, Pyne DB. *Sprinting
+After Having Sprinted: Prior High-Intensity Stochastic Cycling Impairs the Winning Strike for Gold.*
+Front Physiol. 2019;10:100. **PMID 30837886 · DOI 10.3389/fphys.2019.00100.**
+
+---
+
+## Time-trial demands
+
+**✅ Crouch et al. 2017** — review: aerodynamic drag dominates at racing speeds; the rider is ~80% of
+system drag. Crouch TN, Burton D, LaBry ZA, Blair KB. *Riding against the wind: a review of
+competition cycling aerodynamics.* Sports Eng. 2017;20(2):81–110. **DOI 10.1007/s12283-017-0234-1.**
+> The popular "~90% of power to aero at 40 km/h" soundbite traces to **Kyle & Burke 1984**
+> (*Mechanical Engineering*, a trade magazine — **not MEDLINE-indexed, unverifiable, do not cite as
+> primary**). Use Crouch 2017 or Martin 1998 as the verifiable anchor and treat the exact % as
+> approximate.
+
+**✅ Martin et al. 1998** — validated mathematical model of road cycling power (R²=0.97); aero
+dominates on the flat. **No PMID — cite by DOI** (journal not PubMed-indexed). Martin JC,
+Milliken DL, Cobb JE, McFadden KL, Coggan AR. *Validation of a Mathematical Model for Road Cycling
+Power.* J Appl Biomech. 1998;14(3):276–291. **DOI 10.1123/jab.14.3.276.**
+
+**✅ García-López et al. 2008** — wind-tunnel position changes cut pro cyclists' drag ~14%; CdA is
+the primary TT lever. García-López J, Rodríguez-Marroyo JA, Juneau C-E, Peleteiro J, Córdova
+Martínez A, Villa JG. *Reference values and improvement of aerodynamic drag in professional
+cyclists.* J Sports Sci. 2008;26(3):277–286. **PMID 17943597 · DOI 10.1080/02640410701501697.**
+
+**✅ Swain 1997** — vary power on hills/wind (higher into climbs/headwinds) to save TT time. Swain
+DP. *A model for optimizing cycling performance by varying power on hills and in wind.* Med Sci
+Sports Exerc. 1997;29(8):1104–1108. **PMID 9268969 · DOI 10.1097/00005768-199708000-00017.**
+
+**✅ Atkinson, Peacock & Passfield 2007** — updated model: variable pacing on terrain/wind saves
+time; even power near-optimal on flat/windless. Atkinson G, Peacock O, Passfield L. *Variable versus
+constant power strategies during cycling time-trials: prediction of time savings using an up-to-date
+mathematical model.* J Sports Sci. 2007;25(9):1001–1009. **PMID 17497402 · DOI 10.1080/02640410600944709.**
+
+**✅ Smith, Dangelmaier & Hill 1999** — critical power predicts 17-km/40-km TT (r = −0.77 to −0.91),
+more than VT or VO2max. Smith JC, Dangelmaier BS, Hill DW. *Critical power is related to cycling time
+trial performance.* Int J Sports Med. 1999;20(6):374–378. **PMID 10496116 · DOI 10.1055/s-2007-971147.**
+
+*(TT durability draws on Maunder et al. 2021 — see the Durability section above. A dedicated,
+verified HR-reliability-in-TT citation was sought but not confirmed; TT HR guidance defers to
+`data-confounds.md` rather than resting on an unverified source.)*
+
+---
+
 ## Strength training (incl. masters)
 
 **✅ Llanos-Lagos et al. 2026 (epub 2025)** — meta-analysis, 17 studies / 262 cyclists: heavy